© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126912
    Prev
    Next
    INDEX
    Explanations

    mutable state

    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_3_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
    unca
    0.65
     необходимости
    0.61
    s
    0.59
    r
    0.56
    in
    0.55
     frequented
    0.54
     χαρακτη
    0.54
    бора
    0.52
    atation
    0.52
     repaint
    0.52
    POSITIVE LOGITS
    し
    0.74
     are
    0.71
    其他
    0.69
    يب
    0.68
    ری
    0.68
     to
    0.67
    ANT
    0.67
     নিষ্ঠুর
    0.67
    보
    0.66
    ０
    0.65
    Activations Density 0.000%

    No Known Activations