© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206184
    Prev
    Next
    INDEX
    Explanations

    db_name and db_password variables

    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_37_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
     cine
    0.42
    റില്‍
    0.42
     officers
    0.41
    馒
    0.37
    poetry
    0.37
     amn
    0.37
    റിൽ
    0.36
     patch
    0.36
     Voucher
    0.36
     Patch
    0.35
    POSITIVE LOGITS
     (\<
    0.40
    Elliott
    0.40
     इन्होंने
    0.38
    未満
    0.38
     dhatu
    0.38
     articular
    0.37
     Ettha
    0.37
     nenhum
    0.37
     TRANSACTION
    0.37
     Ignition
    0.37
    Activations Density 0.000%

    No Known Activations