© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 117783
    Prev
    Next
    INDEX
    Explanations

    금리, 눈 종류, 병, 길, 빛, 모래, 적

    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_38_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
    𝒏
    0.38
    otherapy
    0.38
    ithing
    0.37
     obviously
    0.36
    बर्ग
    0.36
     যাঁরা
    0.36
     Pathology
    0.36
     Hadley
    0.35
    ቢያ
    0.35
     Neptune
    0.35
    POSITIVE LOGITS
    aule
    0.41
    ekwondo
    0.39
     Focusing
    0.38
     tetragonal
    0.38
    kV
    0.38
    睺
    0.37
    드의
    0.36
     mengandung
    0.36
    苳
    0.36
    ственный
    0.35
    Activations Density 0.001%

    No Known Activations