© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60702
    Prev
    Next
    INDEX
    Explanations

    from this

    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
    _
    0.68
     ح
    0.66
    ANG
    0.64
    dv
    0.63
     На
    0.63
     Shivaji
    0.63
     Ши
    0.58
     않았
    0.58
     మ
    0.57
    pu
    0.56
    POSITIVE LOGITS
    i
    0.82
    on
    0.74
    u
    0.68
    owned
    0.63
    and
    0.61
    ið
    0.57
    בן
    0.56
     tôt
    0.56
    un
    0.55
    ي
    0.55
    Activations Density 0.000%

    No Known Activations