© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59224
    Prev
    Next
    INDEX
    Explanations

    code and punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    物
    0.91
    ature
    0.85
    oid
    0.83
    itude
    0.79
    ไซต์
    0.70
    งาน
    0.64
    phone
    0.63
    siniz
    0.57
    특별시
    0.55
    ritis
    0.54
    POSITIVE LOGITS
    なんだ
    0.40
    Ｔ
    0.38
    anées
    0.37
    adino
    0.36
    dé
    0.36
    incontro
    0.36
    મને
    0.36
    వారి
    0.35
    tsp
    0.35
    西部
    0.34
    Activations Density 0.001%

    No Known Activations