© 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. 86464
    Prev
    Next
    INDEX
    Explanations

    ivory towers, fluid, Ivy Taylor, Frank

    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
    LE
    0.65
    Kako
    0.62
    妸
    0.61
    Ꮘ
    0.61
    鋆
    0.59
    ꩡ
    0.58
     හොඳ
    0.57
     একটা
    0.56
     வரை
    0.56
    OOSE
    0.56
    POSITIVE LOGITS
     are
    0.72
    с
    0.69
    、
    0.66
    ї
    0.66
    ме
    0.64
    in
    0.63
    тор
    0.63
    ！
    0.62
    ے
    0.61
    ре
    0.61
    Activations Density 0.000%

    No Known Activations