© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54598
    Prev
    Next
    INDEX
    Explanations

    names followed by actions or speech

    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_30_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
     বলছি
    0.38
     Micros
    0.38
     unrecognizable
    0.37
    ชัด
    0.37
     Conspiracy
    0.36
    複雑
    0.36
     unfortunately
    0.35
    췌
    0.35
    ApiResponse
    0.34
    abin
    0.34
    POSITIVE LOGITS
    svg
    0.40
     réserver
    0.38
     ecologists
    0.38
     instalar
    0.36
     reservar
    0.36
    ёнок
    0.36
    旨在
    0.36
    වා
    0.34
    onin
    0.34
    symplectic
    0.34
    Activations Density 0.008%

    No Known Activations