© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214006
    Prev
    Next
    INDEX
    Explanations

    shadow or darkness

    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
    म्मे
    0.45
     PAC
    0.43
    tida
    0.40
    IRON
    0.39
     airspeed
    0.38
    鈽
    0.38
     Tid
    0.38
     بند
    0.38
    ريح
    0.38
    PAC
    0.37
    POSITIVE LOGITS
     जान
    0.39
     dw
    0.39
    分析
    0.38
    杫
    0.38
    letos
    0.37
     किराये
    0.37
     DW
    0.37
    inect
    0.37
     TRANSPORTURI
    0.37
     Люд
    0.36
    Activations Density 0.000%

    No Known Activations