© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105702
    Prev
    Next
    INDEX
    Explanations

    Korean, Japanese, German, English characters

    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_1_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
    ut
    1.18
    માં
    1.11
    か
    1.05
    og
    1.01
    ларга
    1.01
    ot
    0.98
    at
    0.96
    un
    0.96
    కు
    0.90
     מפ
    0.89
    POSITIVE LOGITS
    ند
    1.16
    ó
    1.11
     It
    1.05
    رد
    1.01
     If
    0.97
    "
    0.95
    ０
    0.95
     RTL
    0.94
    !"
    0.93
     to
    0.92
    Activations Density 0.000%

    No Known Activations