© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29425
    Prev
    Next
    INDEX
    Explanations

    various languages and contexts

    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_10_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
    n
    0.32
     great
    0.31
    ering
    0.31
    d
    0.30
     لاہور
    0.30
     h
    0.29
     man
    0.29
    ity
    0.29
     H
    0.29
    的概念
    0.29
    POSITIVE LOGITS
    larınız
    0.32
     relatifs
    0.31
    ТР
    0.30
     bạn
    0.30
    ట
    0.29
     ETFs
    0.29
    ك
    0.29
    </h3>
    0.29
    బ్ర
    0.29
     ENGINEERS
    0.29
    Activations Density 0.006%

    No Known Activations