© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125220
    Prev
    Next
    INDEX
    Explanations

    Gomez, Jenner, Algeria, Selene

    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_3_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
    的学生
    0.69
    も
    0.65
    ad
    0.64
     students
    0.57
    quele
    0.55
    q
    0.55
    ại
    0.54
     phenols
    0.54
     бас
    0.54
     scal
    0.53
    POSITIVE LOGITS
    ری
    0.70
    多い
    0.64
    ন
    0.61
    ANTIC
    0.61
    특별시
    0.61
     Algeria
    0.60
    टाइम
    0.59
    ⓝ
    0.58
    >-->
    0.58
     Украї
    0.57
    Activations Density 0.006%

    No Known Activations