© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10835
    Prev
    Next
    INDEX
    Explanations

    instances of enumeration or listing of items

    oai_token-act-pair · gemini-2.0-flash

    namely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ed
    -0.56
    are
    -0.48
    et
    -0.47
    im
    -0.45
    '">
    -0.44
     elétrica
    -0.43
    at
    -0.43
    ']:
    -0.43
    em
    -0.42
     some
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.95
     Вікі
    0.92
    Spoljašnje
    0.90
    ſelf
    0.89
    TagMode
    0.88
    neſs
    0.85
    quelize
    0.84
    +#+#
    0.83
     purpoſe
    0.81
    ſelves
    0.80
    Activations Density 0.935%

    No Known Activations