© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7069
    Prev
    Next
    INDEX
    Explanations

    call or text

    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_39_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
    虻
    0.41
     sinful
    0.39
    ぐる
    0.39
    hav
    0.39
    snail
    0.39
    裒
    0.39
    graded
    0.38
     поль
    0.37
    cN
    0.36
    殁
    0.36
    POSITIVE LOGITS
     validation
    0.42
    exists
    0.40
     validated
    0.38
     bottles
    0.38
     Tuesdays
    0.38
    Exists
    0.37
    ῥ
    0.37
     бого
    0.37
     슈퍼
    0.37
     peptid
    0.36
    Activations Density 0.021%

    No Known Activations