© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127952
    Prev
    Next
    INDEX
    Explanations

    react code snippets

    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
    Negative Logits
    are
    0.93
     are
    0.75
    events
    0.70
    ér
    0.69
     الحمل
    0.68
    ari
    0.66
    v
    0.66
    Bs
    0.62
    osos
    0.62
     الهاتف
    0.62
    POSITIVE LOGITS
    ή
    0.66
    ט
    0.65
    트
    0.65
    는
    0.64
    Α
    0.63
    Ў
    0.63
    '});
    0.62
    ม
    0.62
    ப
    0.61
    ᚨ
    0.60
    Activations Density 0.001%

    No Known Activations