© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135154
    Prev
    Next
    INDEX
    Explanations

    escaped characters and unicode

    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_6_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
    1.13
    :
    0.93
    us
    0.91
    ar
    0.87
    u
    0.85
    inning
    0.84
    a
    0.83
    A
    0.80
    Ent
    0.75
     Years
    0.75
    POSITIVE LOGITS
     будет
    0.69
     إ
    0.67
     ك
    0.67
     ל
    0.67
     כ
    0.67
     puede
    0.63
     имеет
    0.63
     není
    0.63
     etwa
    0.62
     אין
    0.62
    Activations Density 0.001%

    No Known Activations