© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87420
    Prev
    Next
    INDEX
    Explanations

    design intent

    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
    。
    0.73
    。"
    0.73
     Wochen
    0.60
    رم
    0.59
    ）。
    0.56
    。“
    0.56
    ivní
    0.56
    рав
    0.53
     。,
    0.52
    。",
    0.52
    POSITIVE LOGITS
    t
    0.78
    Y
    0.73
    ant
    0.70
    ق
    0.66
    \
    0.65
    ط
    0.65
    m
    0.64
    v
    0.64
    '
    0.63
    ש
    0.63
    Activations Density 0.003%

    No Known Activations