© 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-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122390
    Prev
    Next
    INDEX
    Explanations

    data, albums, input, words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
    Estimate
    0.40
    Associate
    0.38
    Telugu
    0.38
    URCH
    0.38
     dissociated
    0.37
    associate
    0.36
     Valuable
    0.36
    悛
    0.36
    ionalità
    0.36
    flutter
    0.35
    POSITIVE LOGITS
     use
    0.59
     Schubert
    0.40
     used
    0.40
    砲
    0.39
    use
    0.38
     WORD
    0.37
     ਵਰ
    0.37
     suing
    0.36
    用的
    0.35
     uso
    0.35
    Activations Density 0.001%

    No Known Activations