© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9065
    Prev
    Next
    INDEX
    Explanations

    following prepositions or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    拌
    0.54
    또한
    0.54
    $('#
    0.53
    si
    0.52
    u
    0.52
    대
    0.52
    dual
    0.51
    로
    0.50
    π
    0.49
    प्रा
    0.49
    POSITIVE LOGITS
     `<=`
    0.66
    ل
    0.65
     Yhat
    0.64
     hechas
    0.63
    áneo
    0.63
    नरी
    0.62
    losti
    0.61
     tarses
    0.60
     vời
    0.60
     Filipinos
    0.60
    Activations Density 0.270%

    No Known Activations