© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16945
    Prev
    Next
    INDEX
    Explanations

    compile and run

    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_15_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
     petrochemical
    0.16
    ᓂ
    0.16
     Sandberg
    0.16
    MILLISE
    0.16
    אן
    0.16
    ா
    0.16
    ClNO
    0.16
    癬
    0.15
     Pater
    0.15
    CHARACTER
    0.15
    POSITIVE LOGITS
    B
    0.19
     B
    0.19
     L
    0.18
     If
    0.18
    iz
    0.17
    ib
    0.16
     U
    0.15
    V
    0.15
    إ
    0.15
    igated
    0.15
    Activations Density 0.020%

    No Known Activations