© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122833
    Prev
    Next
    INDEX
    Explanations

    SSL TLS JS CSS Tricky agent certificates

    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_3_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
    ।
    0.80
    。
    0.80
    ao
    0.79
    ms
    0.75
     ms
    0.70
    。(
    0.68
    。《
    0.65
    as
    0.64
    MS
    0.63
     MS
    0.63
    POSITIVE LOGITS
    し
    0.73
    ца
    0.68
    ()=>{
    0.65
    ρο
    0.64
    ления
    0.64
    ка
    0.64
    $-\
    0.60
    ਕਰ
    0.56
    ш
    0.56
     I
    0.54
    Activations Density 0.006%

    No Known Activations