© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14448
    Prev
    Next
    INDEX
    Explanations

    timeline creation

    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_40_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
     історії
    0.44
     Carolyn
    0.43
    chron
    0.43
    طيني
    0.43
     तालिका
    0.41
    Keychain
    0.40
    TableModel
    0.40
     историю
    0.40
    순
    0.39
    History
    0.38
    POSITIVE LOGITS
     maturity
    0.43
     reconnect
    0.43
     CONNECT
    0.41
     connect
    0.41
     Connect
    0.41
     loop
    0.40
    iece
    0.40
    接入
    0.40
    CONNECT
    0.39
     control
    0.38
    Activations Density 0.001%

    No Known Activations