© 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. 8901
    Prev
    Next
    INDEX
    Explanations

    Russell

    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
    Not in Any Lists

    No Comments

    Negative Logits
    een
    2.64
    ০০
    2.63
    ે
    2.61
    ाई
    2.41
    นิด
    2.41
    cie
    2.33
    ত
    2.32
    modo
    2.22
    יות
    2.18
    서는
    2.18
    POSITIVE LOGITS
    ي
    2.66
    ity
    2.43
    ில்
    2.31
    ৪
    2.24
    न
    2.23
    й
    2.17
    
    2.16
    檛
    2.16
    щиков
    2.15
    ณฑ
    2.14
    Activations Density 0.000%

    No Known Activations