© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11478
    Prev
    Next
    INDEX
    Explanations

    the word "one" or "two" as well as words that can come before or after those numbers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    interopRequire
    -0.76
    __).
    -0.63
    ')")
    -0.60
     fometimes
    -0.57
    __;
    -0.57
     skeletons
    -0.56
    ]));
    
    -0.54
    :].
    -0.52
     archaeology
    -0.52
     excavation
    -0.52
    POSITIVE LOGITS
     getItemId
    0.56
    clientY
    0.56
    Климат
    0.55
    Билгалдахарш
    0.53
     geslacht
    0.51
     noqa
    0.49
    AnimationsModule
    0.49
     getItemCount
    0.48
    qrstuvwxyz
    0.48
    InputBorder
    0.48
    Activations Density 3.036%

    No Known Activations