© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203040
    Prev
    Next
    INDEX
    Explanations

    TUI, ux, Lindbergh, Tier, Klan

    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_12_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
    '
    0.11
     \]
    0.10
    hene
    0.10
    Decoder
    0.10
    <0xA8>
    0.10
     Commanding
    0.10
     tars
    0.10
    Diversity
    0.10
     Validate
    0.10
     Diversity
    0.09
    POSITIVE LOGITS
     Еўро
    0.13
    эння
    0.13
    壽
    0.13
     ລັບ
    0.12
    점을
    0.12
     शुभकामना
    0.12
    𝕨
    0.12
     опыт
    0.12
     побы
    0.12
    सर्ग
    0.12
    Activations Density 0.001%

    No Known Activations