© 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. 15028
    Prev
    Next
    INDEX
    Explanations

    tokens associated with online activity and commerce

    oai_token-act-pair · gemini-2.0-flash

    online

    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
    AsUp
    -0.63
    esModule
    -0.56
    Бахар
    -0.49
     kiện
    -0.48
     bắc
    -0.47
    schild
    -0.46
     Hurd
    -0.46
     StatefulWidget
    -0.46
    enumi
    -0.45
     OnDestroy
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.71
    :✨
    0.69
    LookAnd
    0.67
    abestanden
    0.65
    Datuak
    0.65
    istoitu
    0.63
    principalTable
    0.56
     للاسماء
    0.53
    الإنجليزية
    0.52
     CURIAM
    0.50
    Activations Density 2.143%

    No Known Activations