© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, lengths

    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
    许
    2.57
    ೇ
    2.53
     sails
    2.52
    courts
    2.44
    ़
    2.39
    地方
    2.34
    पे
    2.33
    वि
    2.31
    การ
    2.31
    大丈夫
    2.29
    POSITIVE LOGITS
     trai
    2.70
    nen
    2.63
    েও
    2.61
    ן
    2.55
    まあ
    2.53
     newdata
    2.35
     lick
    2.35
    まぁ
    2.34
    nent
    2.33
     frustration
    2.32
    Activations Density 0.081%

    No Known Activations