© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30504
    Prev
    Next
    INDEX
    Explanations

    scientists trust atoms

    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_31_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
     sequ
    0.39
    ֗
    0.38
     cuja
    0.37
     cuya
    0.36
     IERC
    0.36
    人で
    0.36
     DMC
    0.36
    rieb
    0.35
     nontrivial
    0.35
     DBC
    0.35
    POSITIVE LOGITS
    を目指
    0.34
    認
    0.33
    "]).
    0.33
     Melanie
    0.33
     variedades
    0.33
     chast
    0.32
     விவசாயிகள்
    0.32
     striking
    0.31
    蜊
    0.31
    вшим
    0.31
    Activations Density 0.039%

    No Known Activations