© 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. 9138
    Prev
    Next
    INDEX
    Explanations

    code syntax and math

    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
    re
    2.63
    י
    2.24
    У
    2.16
    ு
    2.11
     glimpse
    2.08
    М
    2.02
    ⏤
    2.02
     subsequent
    2.02
     বিধান
    2.00
     tambah
    1.97
    POSITIVE LOGITS
    ivative
    2.62
    er
    2.57
    ோர்
    2.38
    ER
    2.36
    $('.
    2.34
    /-}$
    2.31
    frac
    2.25
     conseguir
    2.25
     blessings
    2.24
     있는
    2.24
    Activations Density 0.042%

    No Known Activations