© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215801
    Prev
    Next
    INDEX
    Explanations

    California Institute of Technology

    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_5_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
     revital
    1.20
    。「
    1.09
     código
    1.06
     proteg
    1.05
     is
    1.05
     compass
    1.03
    š
    1.03
    ep
    1.02
     democrat
    1.00
    č
    0.99
    POSITIVE LOGITS
    (
    1.13
    ING
    1.13
    (;
    1.03
    एगी
    1.02
     Afternoon
    1.00
     Ainda
    0.97
    \,\
    0.96
    ANS
    0.93
    ле
    0.92
     Abelian
    0.92
    Activations Density 0.000%

    No Known Activations