© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14438
    Prev
    Next
    INDEX
    Explanations

    Latex code, court filings, and scientific publications

    oai_token-act-pair · gemini-2.0-flash

    Formal documents and papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -1.00
    — 
    -0.95
    !")
    -0.93
     endregion
    -0.91
     Theſe
    -0.89
     itſelf
    -0.88
     myſelf
    -0.87
    UserScript
    -0.86
     disambiguazione
    -0.86
     $_"
    -0.85
    POSITIVE LOGITS
    var
    0.54
    begin
    0.53
    ane
    0.50
    r
    0.45
    mu
    0.43
     становника
    0.42
    mid
    0.42
    0.40
    0.40
    nu
    0.40
    Activations Density 0.565%

    No Known Activations