© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10658
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage audience engagement and feedback

    oai_token-act-pair · gemini-2.0-flash

    asking questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    setVerticalGroup
    -0.67
    RenderAtEndOf
    -0.66
    LookAnd
    -0.65
    HideFlags
    -0.57
    MigrationBuilder
    -0.57
    CloseOperation
    -0.56
     للاسماء
    -0.55
     onAnimation
    -0.54
    DockStyle
    -0.54
     jspb
    -0.53
    POSITIVE LOGITS
    featureID
    0.50
     netts
    0.47
     Betracht
    0.45
     hemsida
    0.44
    Jacket
    0.43
    itename
    0.42
    chedelic
    0.42
    棵
    0.42
    ]}>
    0.42
     rejet
    0.42
    Activations Density 0.572%

    No Known Activations