© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4291
    Prev
    Next
    INDEX
    Explanations

    the HTML entity for a non-breaking space

    oai_token-act-pair · gemini-2.0-flash

    nbsp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     most
    -0.65
    uests
    -0.52
    zések
    -0.49
    ibouti
    -0.48
     greater
    -0.47
    undering
    -0.47
    pons
    -0.47
     die
    -0.47
    nastics
    -0.47
     effective
    -0.46
    POSITIVE LOGITS
    MLLoader
    1.03
     متعلقه
    0.99
    RenderAtEndOf
    0.98
     Jefus
    0.97
    contentLoaded
    0.96
    ScopeManager
    0.90
     Diſ
    0.89
    MessageOf
    0.87
    StoreMessageInfo
    0.87
    ValueStyle
    0.86
    Activations Density 1.385%

    No Known Activations