© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83761
    Prev
    Next
    INDEX
    Explanations

    attorney followed by name or title

    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_0_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
    it
    1.45
    ва
    1.29
    ل
    1.25
    ।
    1.25
    ن
    1.23
    é
    1.20
    ،
    1.19
    дцать
    1.16
    。
    1.12
    ように
    1.09
    POSITIVE LOGITS
    -
    1.74
    '
    1.61
    AL
    1.36
    LE
    1.33
    (
    1.30
    EN
    1.20
    ED
    1.20
     is
    1.19
    IL
    1.16
    的
    1.16
    Activations Density 0.000%

    No Known Activations