© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233517
    Prev
    Next
    INDEX
    Explanations

    trail

    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_46_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
     ആരാധ
    0.37
    rophes
    0.36
    ̮
    0.35
    ⟧
    0.35
     নাটক
    0.35
    ালন
    0.34
    physics
    0.33
    뜬
    0.33
     Тру
    0.33
     principalColumn
    0.33
    POSITIVE LOGITS
     trail
    3.61
    trail
    3.13
     Trail
    3.05
    Trail
    3.02
     trails
    2.91
    trails
    2.48
     Trails
    2.42
    Trails
    2.39
     trailed
    2.14
     TRAILS
    1.98
    Activations Density 0.071%

    No Known Activations