© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    words and phrases used within technical or formal explanations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     doInBackground
    -0.62
     personnalité
    -0.57
     tect
    -0.52
    JsonHelper
    -0.52
     viewType
    -0.51
    <bos>
    -0.50
    Portale
    -0.47
    niosek
    -0.47
    ParallelGroup
    -0.47
    مون
    -0.46
    POSITIVE LOGITS
    migrationBuilder
    0.82
    ukone
    0.66
    rceil
    0.61
    enderror
    0.60
     />);
    0.60
     NSCoder
    0.59
    ']):
    0.58
    !*\
    0.55
    ')}}">
    0.54
    mergeFrom
    0.54
    Activations Density 21.680%

    No Known Activations