© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9599
    Prev
    Next
    INDEX
    Explanations

    sentences in German involving authority figures, honey, legal processes, and grammar

    oai_token-act-pair · gemini-2.0-flash

    diverse concepts and terms in various languages

    np_token-act-pair-logits · gpt-4o-mini

    itatMethod number: 4, reason: could not find any other pattern, explanation: itat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reactstrap
    -0.91
    VersionUID
    -0.91
    expandindo
    -0.89
     saites
    -0.88
    بوابة
    -0.85
    SourceChecksum
    -0.85
    TagMode
    -0.83
     дописавши
    -0.82
    Autoritní
    -0.81
    MemoryWarning
    -0.80
    POSITIVE LOGITS
     duração
    0.42
     nuvem
    0.35
    secta
    0.34
     of
    0.33
    .
    0.33
     معرف
    0.32
     equipaje
    0.32
    arthritis
    0.32
     terá
    0.32
     acercarse
    0.31
    Activations Density 3.964%

    No Known Activations