© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43795
    Prev
    Next
    INDEX
    Explanations

    lower body

    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
    ח
    0.80
    خ
    0.79
    상
    0.71
    ک
    0.66
    لا
    0.66
    नंतर
    0.65
    لم
    0.64
     ouvrage
    0.64
    상은
    0.63
    رض
    0.62
    POSITIVE LOGITS
    .
    0.91
     lower
    0.83
    in
    0.71
     .
    0.71
    o
    0.71
    .。
    0.69
    3
    0.68
     Lower
    0.67
     niž
    0.66
     ниж
    0.64
    Activations Density 0.030%

    No Known Activations