© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    money and businesses

    oai_token-act-pair · gemini-2.0-flash

    Investing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    writeField
    -0.52
     poveznice
    -0.46
    isio
    -0.45
     public
    -0.42
    CAPTION
    -0.42
     aperta
    -0.41
     doigt
    -0.41
     active
    -0.41
     Junior
    -0.41
    twimg
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.89
     reinvest
    0.86
     investing
    0.82
    RectangleBorder
    0.77
     Investing
    0.77
    ImageContext
    0.76
     مشين
    0.75
     investi
    0.74
     invest
    0.74
     invests
    0.74
    Activations Density 1.866%

    No Known Activations