© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97346
    Prev
    Next
    INDEX
    Explanations

    datasource configuration

    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_14_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
    熵
    0.57
    "—
    0.53
    賏
    0.53
    胙
    0.52
     فرزند
    0.51
    枤
    0.50
     செய்து
    0.50
     کاروبار
    0.50
    ᐳ
    0.50
    きる
    0.50
    POSITIVE LOGITS
    he
    0.60
    not
    0.59
    ri
    0.55
    no
    0.54
    ovac
    0.54
    non
    0.54
    mau
    0.53
    values
    0.52
    mathrm
    0.51
    Guide
    0.51
    Activations Density 0.000%

    No Known Activations