© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127869
    Prev
    Next
    INDEX
    Explanations

    due to licensing restrictions

    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_37_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
     Effort
    0.38
     بسبب
    0.37
    MPC
    0.37
     Convenience
    0.37
     effort
    0.36
    😟
    0.36
    能力
    0.35
    利益
    0.35
     (((
    0.35
    LJ
    0.35
    POSITIVE LOGITS
     confusion
    0.41
     fatalities
    0.39
     riots
    0.38
     robberies
    0.38
     fab
    0.37
     them
    0.37
     robbery
    0.36
     stále
    0.35
     aver
    0.35
    fab
    0.35
    Activations Density 0.007%

    No Known Activations