© 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. 150041
    Prev
    Next
    INDEX
    Explanations

    @objc func

    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
     kk
    0.49
     corals
    0.47
     ahuv
    0.46
     watercolors
    0.45
    elola
    0.43
     सागरी
    0.43
    افه
    0.42
     각
    0.42
     pabbaj
    0.42
     labors
    0.42
    POSITIVE LOGITS
     Pri
    0.55
    Gar
    0.45
     Bur
    0.43
     Par
    0.41
    Pri
    0.40
     Pan
    0.40
     Bour
    0.40
    Max
    0.39
     Prior
    0.39
     Coyote
    0.39
    Activations Density 0.000%

    No Known Activations