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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12045
    Prev
    Next
    INDEX
    Explanations

    language about responsibilities and obligations

    oai_token-act-pair · gemini-2.0-flash

    terminology related to responsibility and authority

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

    responsible

    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
    évaluateur
    -0.49
    naden
    -0.49
     direct
    -0.49
     responsible
    -0.48
     rapid
    -0.48
    oredCriteria
    -0.47
    pt
    -0.47
    udin
    -0.47
     муніципалі
    -0.45
    lgari
    -0.45
    POSITIVE LOGITS
     fotografico
    0.73
    RUnlock
    0.69
    StructEnd
    0.65
    URLException
    0.65
    yntaxException
    0.63
     становника
    0.59
     BorderRadius
    0.57
     Viber
    0.57
    EndContext
    0.57
    basicConfig
    0.56
    Activations Density 5.721%

    No Known Activations