© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210893
    Prev
    Next
    INDEX
    Explanations

    various languages and accents

    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_5_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
    ä
    1.38
    ig
    1.20
    og
    1.20
    >
    1.17
     p
    1.14
    ↵↵
    1.13
    eg
    1.13
    ale
    1.13
    ling
    1.10
    ala
    1.10
    POSITIVE LOGITS
     drugih
    1.00
     giocatore
    0.99
    󰡔
    0.97
     chiam
    0.96
     établ
    0.94
    targetContext
    0.94
    的其他
    0.94
    辿
    0.94
    ம்
    0.93
    的时
    0.93
    Activations Density 0.000%

    No Known Activations