© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35037
    Prev
    Next
    INDEX
    Explanations

    problem. failure. violence. route

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ANOTHER
    0.56
     terus
    0.55
    이
    0.55
     alasan
    0.54
     étrangers
    0.54
    ΑΣ
    0.53
     merav
    0.53
     tersangka
    0.52
    ފ
    0.52
    ∖
    0.52
    POSITIVE LOGITS
    ant
    0.60
    v
    0.58
    er
    0.56
    ol
    0.56
    able
    0.54
    ine
    0.54
    r
    0.54
    id
    0.53
    ចេ
    0.52
     hand
    0.52
    Activations Density 0.000%

    No Known Activations