© 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. 6470
    Prev
    Next
    INDEX
    Explanations

    code snippets and website/application development terms.

    oai_token-act-pair · gemini-2.0-flash

    word "call"

    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
     виправивши
    -0.86
     boards
    -0.85
    boards
    -0.81
     Boards
    -0.77
     board
    -0.76
     Board
    -0.74
    BOARD
    -0.74
    Board
    -0.73
    board
    -0.72
     BOARD
    -0.70
    POSITIVE LOGITS
     call
    0.63
    call
    0.59
     calls
    0.56
    Call
    0.55
     Call
    0.54
     Calls
    0.48
     calling
    0.47
    调用
    0.47
    CALL
    0.46
    呼
    0.45
    Activations Density 1.314%

    No Known Activations