© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141138
    Prev
    Next
    INDEX
    Explanations

    documentation and wiki templates

    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_12_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
     D
    0.46
    ville
    0.39
    ga
    0.39
    chool
    0.39
    dato
    0.38
    ling
    0.37
    dense
    0.37
    dans
    0.37
    y
    0.37
     "
    0.37
    POSITIVE LOGITS
     beverages
    0.40
     acom
    0.39
    ICKET
    0.39
     cues
    0.39
     torches
    0.39
    н
    0.39
    ວ່າ
    0.38
    बरा
    0.38
    QUES
    0.38
    푝
    0.38
    Activations Density 0.001%

    No Known Activations