© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201859
    Prev
    Next
    INDEX
    Explanations

    h

    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_37_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
    坻
    0.42
    hours
    0.40
    Tov
    0.40
     horas
    0.39
    ≒
    0.37
    ቶች
    0.37
    молу
    0.37
     hours
    0.37
    цеп
    0.36
     घण्ट
    0.36
    POSITIVE LOGITS
     UIS
    0.42
     раздела
    0.42
    шении
    0.40
     brunes
    0.38
     পড়িল
    0.38
     bu
    0.38
    ையம்
    0.37
    氤
    0.37
    앉
    0.36
     दरभंगा
    0.36
    Activations Density 0.000%

    No Known Activations