© 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. 91659
    Prev
    Next
    INDEX
    Explanations

    engine performance and management

    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
    حم
    0.84
    ICK
    0.67
    الي
    0.64
    টা
    0.63
    ן
    0.63
    ח
    0.61
     cinci
    0.60
    ில்
    0.59
     البيت
    0.59
    يني
    0.58
    POSITIVE LOGITS
    р
    1.03
    ।
    0.92
    。
    0.90
    )
    0.83
    ル
    0.79
    ž
    0.78
    be
    0.77
    ર
    0.75
    ｆ
    0.74
    ко
    0.74
    Activations Density 0.001%

    No Known Activations