© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80191
    Prev
    Next
    INDEX
    Explanations

    dribbling or pyrotechnics

    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_0_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
    O
    1.86
    AR
    1.84
    AL
    1.63
     a
    1.58
     I
    1.52
    1
    1.52
    ING
    1.40
     \
    1.35
    Ol
    1.34
    AT
    1.31
    POSITIVE LOGITS
    cję
    1.54
     Фран
    1.45
    k
    1.45
    ről
    1.42
    kval
    1.38
    re
    1.35
     Спо
    1.34
    सदीय
    1.34
     Сасик
    1.34
    ꔰ
    1.33
    Activations Density 0.000%

    No Known Activations