© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11282
    Prev
    Next
    INDEX
    Explanations

    words relating to pulling or being pulled

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AccessorTable
    -0.69
    IContainer
    -0.63
     hẹn
    -0.63
     geométrico
    -0.62
    LLABLE
    -0.61
    ไซ
    -0.60
    Koordinaten
    -0.60
     beep
    -0.60
    arbeitet
    -0.60
    WarningLevel
    -0.59
    POSITIVE LOGITS
     pulled
    0.96
    DRAW
    0.94
    pull
    0.94
     Pull
    0.93
     drawn
    0.93
     pull
    0.93
    Pull
    0.91
     Drawn
    0.90
     pulling
    0.90
     drawing
    0.88
    Activations Density 0.698%

    No Known Activations