© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126526
    Prev
    Next
    INDEX
    Explanations

    model 9

    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_37_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
     pengurangan
    0.39
     différent
    0.38
     pérd
    0.37
     customtkinter
    0.36
     asegurarse
    0.36
    ♐
    0.36
    <0x04>
    0.36
    ="'$(
    0.35
     उच्च
    0.35
     мае
    0.35
    POSITIVE LOGITS
    Đ
    0.39
    С
    0.36
    device
    0.36
    init
    0.35
    la
    0.33
    Σ
    0.33
    router
    0.33
    Dear
    0.33
    uid
    0.33
    Да
    0.33
    Activations Density 0.018%

    No Known Activations