© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    matlab code blocks

    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
    ள்
    1.08
    ية
    0.99
    াল
    0.91
    \%$
    0.88
    א
    0.87
     građ
    0.87
    kaç
    0.86
     supremum
    0.85
    нение
    0.84
     זאת
    0.83
    POSITIVE LOGITS
    𝐞
    0.96
    শালী
    0.89
    𝐭
    0.86
    urized
    0.85
    𝐒
    0.84
    ン
    0.83
    itudes
    0.83
    odiazep
    0.82
    可以说
    0.82
     consents
    0.81
    Activations Density 0.003%

    No Known Activations