© 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. 12682
    Prev
    Next
    INDEX
    Explanations

    quotation marks or numbers

    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
    ಜು
    0.15
     використо
    0.15
     använd
    0.15
    髅
    0.14
    ictionaries
    0.14
    зера
    0.14
     вони
    0.13
    ্তিক
    0.13
    囔
    0.13
     unimplemented
    0.13
    POSITIVE LOGITS
     Ban
    0.13
     fume
    0.13
    WA
    0.12
     bio
    0.12
     BAN
    0.12
     discovery
    0.12
     memang
    0.11
    dynam
    0.11
    非常有
    0.11
    poss
    0.11
    Activations Density 0.005%

    No Known Activations