© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12930
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to tables and formatting

    oai_token-act-pair · gemini-2.0-flash

    </td>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Monfieur
    -0.70
    הערות
    -0.69
    ']).
    -0.69
     تضيفلها
    -0.69
     calldata
    -0.68
    aarrggbb
    -0.68
     Cæsar
    -0.68
    "}")
    -0.65
    isContained
    -0.65
     -}
    -0.64
    POSITIVE LOGITS
     Multi
    0.41
    SequentialGroup
    0.39
     الاطلاع
    0.38
     transfieras
    0.37
     AssemblyProduct
    0.37
     Jüng
    0.37
    Multi
    0.36
    Multiplier
    0.36
    <eos>
    0.36
     I
    0.36
    Activations Density 2.640%

    No Known Activations