© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1387
    Prev
    Next
    INDEX
    Explanations

    email subjects and greetings

    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_39_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
     zog
    0.39
    OHA
    0.38
    _);
    0.37
    🍶
    0.37
    ารถ
    0.37
    enderita
    0.37
    ソフトウェア
    0.37
    destruction
    0.37
    ࢮ
    0.36
    igenous
    0.36
    POSITIVE LOGITS
     cool
    0.39
     shell
    0.38
     বায়
    0.38
     heart
    0.38
     stand
    0.38
     dy
    0.38
     conf
    0.37
     post
    0.37
     perishable
    0.37
     wall
    0.37
    Activations Density 0.000%

    No Known Activations