© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148283
    Prev
    Next
    INDEX
    Explanations

    and so on

    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_23_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
    ،
    0.43
    oyeva
    0.42
     و
    0.40
    ፣
    0.39
     छापा
    0.37
     và
    0.37
    Airbnb
    0.37
     και
    0.37
    ripcion
    0.36
    !
    0.36
    POSITIVE LOGITS
     debts
    0.45
     boundaries
    0.42
     sorun
    0.42
     overtly
    0.42
     aggression
    0.40
     puns
    0.40
     ailes
    0.40
     aggressiveness
    0.39
     registries
    0.39
     Предпо
    0.39
    Activations Density 0.001%

    No Known Activations