© 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. 91020
    Prev
    Next
    INDEX
    Explanations

    particular [noun]

    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
    '
    1.08
    ל
    0.97
    0.93
    って
    0.87
    ני
    0.81
    ความ
    0.81
    いた
    0.80
    นี้
    0.79
    มีความ
    0.79
    ação
    0.76
    POSITIVE LOGITS
    y
    0.85
     فريبي
    0.71
    ام
    0.70
    ت
    0.70
    yó
    0.68
    ي
    0.67
     použit
    0.66
    ၷ
    0.65
    两
    0.64
     ors
    0.64
    Activations Density 0.002%

    No Known Activations