© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210796
    Prev
    Next
    INDEX
    Explanations

    facture, лом, 桥

    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_5_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
    in
    1.80
    1
    1.39
    ip
    1.23
    し
    1.20
    ות
    1.16
     Биз
    1.12
    ла
    1.11
    9
    1.10
    ۱
    1.09
    re
    1.08
    POSITIVE LOGITS
    ↵
    1.32
    h
    1.22
    -
    1.04
    lige
    0.98
    ם
    0.97
    اه
    0.94
    lv
    0.86
    ierte
    0.85
    elt
    0.82
    d
    0.82
    Activations Density 0.000%

    No Known Activations