© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149476
    Prev
    Next
    INDEX
    Explanations

    discriminant value

    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_23_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
     users
    0.42
     polit
    0.41
     LinkedIn
    0.41
     voters
    0.41
     ISPs
    0.40
    {
    0.40
     usuarios
    0.40
    Improve
    0.40
     Zem
    0.39
    ിക്ക
    0.39
    POSITIVE LOGITS
     ؛
    0.43
    сні
    0.41
     আবিষ্কার
    0.40
    夭
    0.40
    сування
    0.39
    жина
    0.39
    кі
    0.38
    จีน
    0.38
    ників
    0.37
     درسنا
    0.37
    Activations Density 0.000%

    No Known Activations