© 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. 86587
    Prev
    Next
    INDEX
    Explanations

    Park

    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
    t
    0.66
    AA
    0.65
    ა
    0.64
    ку
    0.59
    بد
    0.59
    ۹
    0.58
    اج
    0.57
    č
    0.57
    ان
    0.57
    skap
    0.56
    POSITIVE LOGITS
     с
    0.66
     denote
    0.60
    ы
    0.58
     titoli
    0.57
    ти
    0.57
     întâ
    0.56
     у
    0.55
     كلمات
    0.55
     ي
    0.55
     asin
    0.55
    Activations Density 0.000%

    No Known Activations