© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133748
    Prev
    Next
    INDEX
    Explanations

    innermost, Brand, Reaction

    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_1_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
    ية
    1.15
    _
    1.15
    RO
    1.09
    ON
    1.06
    3
    1.05
    ри
    1.02
    ला
    1.00
    \
    0.99
    >
    0.97
    OM
    0.97
    POSITIVE LOGITS
    i
    1.08
    ’
    0.95
    x
    0.89
    も
    0.88
    عه
    0.78
    ments
    0.77
    Posted
    0.76
     I
    0.74
    This
    0.73
    Promotion
    0.73
    Activations Density 0.000%

    No Known Activations