© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36162
    Prev
    Next
    INDEX
    Explanations

    wavy hair

    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_11_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
    слови
    0.54
    ’
    0.52
    はお
    0.50
    '
    0.49
     أنها
    0.47
    م
    0.47
    ிறார்கள்
    0.47
     е
    0.47
     গলায়
    0.46
     определён
    0.46
    POSITIVE LOGITS
    u
    0.95
    ות
    0.64
    s
    0.63
    ll
    0.62
    šk
    0.59
    ष्
    0.59
     mai
    0.59
     feudal
    0.58
    ла
    0.57
    c
    0.57
    Activations Density 0.005%

    No Known Activations