© 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. 9190
    Prev
    Next
    INDEX
    Explanations

    svg code

    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
    꼴
    0.96
    व
    0.89
    되지
    0.86
     coercive
    0.85
    г
    0.83
    (?:
    0.83
    $
    0.82
    0.82
     supernatants
    0.80
    queros
    0.80
    POSITIVE LOGITS
    ar
    1.41
    ا
    1.37
    a
    1.12
    ার
    1.12
    د
    1.10
     teda
    1.06
    ্ড
    1.03
    ात
    1.03
     encomenda
    1.01
    generalized
    1.00
    Activations Density 0.000%

    No Known Activations