© 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. 80715
    Prev
    Next
    INDEX
    Explanations

    access token

    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
     a
    1.55
     or
    1.09
    ilerini
    1.03
     fertil
    1.02
     that
    1.00
    fection
    0.97
     you
    0.96
     who
    0.96
     lunchtime
    0.96
    ેટ
    0.93
    POSITIVE LOGITS
    ع
    2.03
    ح
    1.82
    ف
    1.59
    l
    1.54
    علم
    1.52
    ش
    1.52
    m
    1.47
    ج
    1.45
    ro
    1.38
    ן
    1.34
    Activations Density 0.001%

    No Known Activations