© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209445
    Prev
    Next
    INDEX
    Explanations

    tangent

    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_25_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
    ئي
    0.46
    étiques
    0.44
    duplicates
    0.41
    Mitt
    0.41
    curve
    0.41
    meshes
    0.41
    溧
    0.41
    ahoma
    0.40
    ached
    0.40
    selves
    0.40
    POSITIVE LOGITS
     በአ
    0.42
     በእ
    0.39
     Hosting
    0.38
    طنين
    0.38
    दन
    0.37
     सत्तार
    0.37
     대
    0.37
     administer
    0.37
     美国
    0.37
     Managing
    0.36
    Activations Density 0.000%

    No Known Activations