© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13013
    Prev
    Next
    INDEX
    Explanations

    code and math formulas

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    DoubleQuotes
    -0.84
    ViewFeatures
    -0.81
    .*")]
    -0.73
     Efq
    -0.71
     myſelf
    -0.68
    
    -0.67
     فريبيس
    -0.66
    </tfoot>
    -0.65
     StatelessWidget
    -0.65
    UnitTesting
    -0.64
    POSITIVE LOGITS
    IANGLES
    0.57
    istoitu
    0.57
    ledem
    0.54
    URIComponent
    0.51
    ruptedException
    0.51
    uckles
    0.51
     alleviation
    0.51
    getColumnIndex
    0.49
    gelopen
    0.49
    annica
    0.49
    Activations Density 1.397%

    No Known Activations