© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14825
    Prev
    Next
    INDEX
    Explanations

    code snippets consisting with question answer pairs with code, links, or definitions.

    oai_token-act-pair · gemini-2.0-flash

    technical/programming content

    np_max-act · 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
     AssemblyProduct
    -0.51
    !');
    -0.47
    Brainz
    -0.46
    AutoScaleMode
    -0.45
    帖最后由
    -0.45
    řej
    -0.45
    ()];
    -0.45
    ']}
    -0.44
    .');
    -0.44
     adipis
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.54
    msgSender
    0.54
    ContentAsync
    0.52
     initComponents
    0.51
    urazione
    0.51
     Roskov
    0.51
     مشين
    0.50
     Reverso
    0.50
     للاسماء
    0.49
    XmlType
    0.49
    Activations Density 0.890%

    No Known Activations