© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83674
    Prev
    Next
    INDEX
    Explanations

    class member names

    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_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    java
    0.48
    rounding
    0.44
    legislation
    0.42
    jax
    0.42
    ="${
    0.41
    jav
    0.40
    bumptech
    0.40
    éditeur
    0.40
    boolean
    0.39
     及
    0.39
    POSITIVE LOGITS
     admitted
    0.43
    芢
    0.40
     admits
    0.39
     Allo
    0.39
     ston
    0.39
     listed
    0.38
     positively
    0.38
    стон
    0.37
     sign
    0.37
     Pflege
    0.37
    Activations Density 0.003%

    No Known Activations