© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77066
    Prev
    Next
    INDEX
    Explanations

    International, SUN, WS, Bitcoin, Eras, crypt, Digital, App

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accuracy
    0.37
     vj
    0.37
    proficiency
    0.37
    itumor
    0.37
     specificity
    0.36
    //!
    0.36
    popularity
    0.35
    统
    0.35
     店
    0.34
    $'
    0.34
    POSITIVE LOGITS
    uerre
    0.35
    ႉ
    0.35
     puer
    0.35
     pouco
    0.35
     pequenas
    0.34
     зем
    0.34
    રમાં
    0.34
    vili
    0.34
    ലം
    0.34
    uração
    0.33
    Activations Density 0.000%

    No Known Activations