© 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. 151207
    Prev
    Next
    INDEX
    Explanations

    cod

    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
    ept
    0.43
    澼
    0.41
    étel
    0.39
    avage
    0.37
    acylglycer
    0.36
    ുപത്രി
    0.36
    乸
    0.36
    agascar
    0.35
    eville
    0.35
    のリ
    0.35
    POSITIVE LOGITS
    ing
    0.44
    ઓએ
    0.38
    need
    0.37
    N
    0.36
    YO
    0.36
    addressed
    0.35
    oy
    0.35
    Menu
    0.34
    amen
    0.34
    ATT
    0.34
    Activations Density 0.000%

    No Known Activations