© 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. 14458
    Prev
    Next
    INDEX
    Explanations

    a mixture of numbers, the letter "e", code snippets, programming terms, and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    terms related to the letter 'e' and its usage

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

    7

    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
    GEBURTSDATUM
    -0.74
    Odkazy
    -0.69
    setViewName
    -0.69
     &___
    -0.68
    Personendaten
    -0.68
    Datuak
    -0.67
    RectangleBorder
    -0.66
    ">//
    -0.65
    \{\\
    -0.65
    Спасылкі
    -0.65
    POSITIVE LOGITS
    eah
    0.47
     rewind
    0.46
     consumed
    0.44
     consuma
    0.43
    不像
    0.43
    itron
    0.42
     reused
    0.41
    nez
    0.40
    aws
    0.40
    eren
    0.40
    Activations Density 20.007%

    No Known Activations