© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141642
    Prev
    Next
    INDEX
    Explanations

    requirement

    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_0_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
    न
    1.64
    1.47
    ن
    1.42
    ll
    1.17
    },
    1.16
    x
    1.14
    ri
    1.06
    ge
    1.06
    ン
    1.06
    liği
    1.02
    POSITIVE LOGITS
    to
    1.77
    ی
    1.57
    ม
    1.55
    рта
    1.52
    dır
    1.50
    нг
    1.48
    is
    1.47
    ння
    1.46
    ت
    1.46
     be
    1.45
    Activations Density 0.000%

    No Known Activations