© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33367
    Prev
    Next
    INDEX
    Explanations

    states or actions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     а
    0.50
     अ
    0.43
     아
    0.41
     আ
    0.40
    ဃ
    0.40
    𒀊
    0.39
     भागों
    0.38
    нду
    0.38
     الحركه
    0.38
    𝐚
    0.38
    POSITIVE LOGITS
    שרה
    0.36
    reet
    0.36
    ষ্কার
    0.35
     cour
    0.35
     Bad
    0.35
     anytime
    0.34
    course
    0.34
    ','.
    0.34
     course
    0.34
    ێت
    0.34
    Activations Density 0.004%

    No Known Activations