© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86383
    Prev
    Next
    INDEX
    Explanations

    gensymb, gensim, motor, regulatory networks

    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
    ’
    0.67
    jší
    0.65
    ))
    0.59
    AJ
    0.59
    A
    0.57
     bootcamp
    0.56
     slog
    0.54
    ):
    0.53
    N
    0.53
    O
    0.52
    POSITIVE LOGITS
    n
    0.93
    ad
    0.90
    ла
    0.79
    ین
    0.79
    ير
    0.69
    p
    0.69
    ارك
    0.68
    اي
    0.66
    น
    0.65
     can
    0.65
    Activations Density 0.017%

    No Known Activations