© 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. 46527
    Prev
    Next
    INDEX
    Explanations

    CIDR block notation

    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
    d
    1.14
    of
    0.92
    t
    0.91
    dır
    0.76
    ів
    0.75
    dı
    0.74
    み
    0.73
    ู
    0.73
    ма
    0.72
    ะ
    0.71
    POSITIVE LOGITS
     Cyborg
    0.69
    uted
    0.64
    ح
    0.64
     Giron
    0.63
     que
    0.62
    )。
    0.60
     Montenegro
    0.60
     Ники
    0.59
    rukt
    0.59
     подготов
    0.58
    Activations Density 0.003%

    No Known Activations