© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8149
    Prev
    Next
    INDEX
    Explanations

    instructions or structured data formats

    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_40_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
     constante
    0.33
    ()}')
    0.33
     constantes
    0.32
     constant
    0.32
     nombre
    0.31
     zeit
    0.31
     दत्ता
    0.31
    ponin
    0.31
     pohy
    0.31
    蔦
    0.31
    POSITIVE LOGITS
    List
    0.34
    Format
    0.33
    ^{-}$
    0.33
    Sources
    0.32
    verture
    0.31
    FORMAT
    0.31
     লিস্ট
    0.31
     List
    0.31
     Sources
    0.31
    veck
    0.30
    Activations Density 0.023%

    No Known Activations