© 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. 206692
    Prev
    Next
    INDEX
    Explanations

    UID and GID mapping

    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
     amines
    0.16
     these
    0.16
     പോലെ
    0.15
     i
    0.15
     Jor
    0.15
    狲
    0.15
     this
    0.15
     มิ
    0.15
     ordres
    0.15
     entrees
    0.15
    POSITIVE LOGITS
    การ
    0.17
    ved
    0.15
    ס
    0.15
    ath
    0.14
    ния
    0.14
    ودة
    0.14
    et
    0.14
    ம்
    0.14
    ための
    0.13
     waxay
    0.13
    Activations Density 0.001%

    No Known Activations