© 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. 11867
    Prev
    Next
    INDEX
    Explanations

    HTML or Javascript code

    oai_token-act-pair · gemini-2.0-flash

    Code and JavaScript

    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
     [*]
    -0.45
    ёл
    -0.44
     PR
    -0.44
    |"
    -0.44
    \|_{
    -0.43
     rest
    -0.42
     clientId
    -0.41
    重
    -0.41
     cork
    -0.41
    addOn
    -0.41
    POSITIVE LOGITS
    principalColumn
    0.73
     transfieras
    0.71
     peines
    0.71
    VIAF
    0.71
    migrationBuilder
    0.70
     feroit
    0.68
    thâu
    0.64
    脚注の使い方
    0.63
    OGND
    0.63
    ItemBackground
    0.61
    Activations Density 0.010%

    No Known Activations