© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14661
    Prev
    Next
    INDEX
    Explanations

    the beginning of events, like opening times, starts, debuts, and premieres

    oai_token-act-pair · gemini-2.0-flash

    starting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    consin
    -0.59
    lyl
    -0.57
    ništ
    -0.57
    ENDIX
    -0.57
    writeField
    -0.56
    gäng
    -0.54
    tisol
    -0.54
    migrationBuilder
    -0.54
    érard
    -0.54
    IInter
    -0.53
    POSITIVE LOGITS
    Diweddarwch
    0.74
    start
    0.68
     starts
    0.65
     Start
    0.65
     start
    0.65
    Start
    0.63
    starts
    0.63
    Begin
    0.60
     started
    0.60
    Starts
    0.60
    Activations Density 2.915%

    No Known Activations