© 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. 206800
    Prev
    Next
    INDEX
    Explanations

    Federal Zone

    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
     привести
    0.40
    尕
    0.37
     Deo
    0.36
    gitian
    0.35
    信任
    0.35
     mumkin
    0.35
    renn
    0.35
    wdir
    0.35
     }^{[
    0.34
    adang
    0.34
    POSITIVE LOGITS
    認識
    0.40
     realizacji
    0.38
    غو
    0.37
     Schenectady
    0.36
    management
    0.36
     réalisation
    0.35
    ար
    0.35
     realizes
    0.35
    ঢাকা
    0.35
    帅
    0.35
    Activations Density 0.002%

    No Known Activations