© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162788
    Prev
    Next
    INDEX
    Explanations

    motorsport manager

    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_2_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
    <0x80>
    1.48
    and
    1.17
    ен
    1.14
    al
    1.09
    de
    1.06
    ed
    0.99
    ere
    0.98
    -
    0.98
    ;
    0.96
     sports
    0.95
    POSITIVE LOGITS
    padă
    1.15
    Retour
    1.15
    ক
    1.12
    ]];
    1.09
    )$;
    1.06
    ਾ
    1.06
    ल
    1.04
    к
    1.04
    ן
    1.04
    ()=>{
    1.03
    Activations Density 0.000%

    No Known Activations