© 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. 38963
    Prev
    Next
    INDEX
    Explanations

    nifi

    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
    ה
    1.10
     collinear
    0.79
    ва
    0.78
    '
    0.78
     l
    0.77
    ه
    0.77
    ７
    0.76
    ﾗ
    0.76
     is
    0.75
    η
    0.74
    POSITIVE LOGITS
    Statement
    0.76
    Status
    0.75
    0.71
    Module
    0.70
    Cable
    0.68
    t
    0.68
    Threads
    0.68
    ank
    0.67
    Motion
    0.67
    Carousel
    0.67
    Activations Density 0.003%

    No Known Activations