© 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. 36125
    Prev
    Next
    INDEX
    Explanations

    near-infrared or perfect

    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
    eeee
    0.64
     cercanos
    0.64
     күн
    0.63
    附近
    0.62
     Мария
    0.61
    <
    0.61
    gam
    0.59
     ведет
    0.59
    gue
    0.59
    '
    0.59
    POSITIVE LOGITS
    ار
    0.79
    on
    0.77
    し
    0.75
    ر
    0.74
    е
    0.72
     is
    0.70
    ра
    0.68
    at
    0.67
    ות
    0.67
    لة
    0.67
    Activations Density 0.002%

    No Known Activations