© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66712
    Prev
    Next
    INDEX
    Explanations

    Web

    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_51_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
     SCO
    0.40
     sü
    0.40
     Brod
    0.39
    ♤
    0.39
    SCO
    0.38
     Bache
    0.37
     SH
    0.37
     SUD
    0.36
    里
    0.36
     Tada
    0.36
    POSITIVE LOGITS
    Web
    1.09
     Web
    1.05
    web
    0.96
     Webb
    0.96
     web
    0.95
    WEB
    0.94
    ウェブ
    0.91
     webbing
    0.89
     веб
    0.86
     Webs
    0.83
    Activations Density 0.000%

    No Known Activations