© 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. 156754
    Prev
    Next
    INDEX
    Explanations

    J

    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
    adev
    0.39
    igil
    0.38
    ිර
    0.38
    大战
    0.37
    贷
    0.37
    ב
    0.36
    árd
    0.35
    巖
    0.35
    igen
    0.35
    வார்
    0.35
    POSITIVE LOGITS
     J
    0.89
    J
    0.79
    𝐽
    0.65
     j
    0.58
    Ｊ
    0.57
     ജെ
    0.55
     الج
    0.55
     ज
    0.54
     ஜ
    0.54
    𝗝
    0.52
    Activations Density 0.000%

    No Known Activations