© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39105
    Prev
    Next
    INDEX
    Explanations

    Chinese, Vietnamese, and names

    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_3_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
    ح
    0.72
    ᴛ
    0.70
    며
    0.66
    وج
    0.64
    ش
    0.64
    ors
    0.63
    ことにより
    0.63
    loans
    0.61
    т
    0.61
    /
    0.58
    POSITIVE LOGITS
    h
    0.70
    ágina
    0.64
    وريا
    0.63
     stata
    0.62
    ﺁ
    0.62
     {})
    0.61
    骡
    0.61
     successivo
    0.60
    र्पण
    0.60
     indignant
    0.60
    Activations Density 0.000%

    No Known Activations