© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36613
    Prev
    Next
    INDEX
    Explanations

    pure functions

    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
    н
    0.72
    то
    0.67
     نہيں
    0.60
     पारा
    0.60
    ieurs
    0.58
     විශ
    0.57
     لیګ
    0.57
    므
    0.57
    ientôt
    0.56
    ų
    0.56
    POSITIVE LOGITS
    A
    0.88
    ول
    0.71
    T
    0.70
    O
    0.65
     (
    0.63
    AL
    0.63
    L
    0.63
    P
    0.62
    M
    0.61
    H
    0.61
    Activations Density 0.009%

    No Known Activations