© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77340
    Prev
    Next
    INDEX
    Explanations

    Man

    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_53_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
    考
    0.40
    oir
    0.38
     আত্মীয়
    0.38
    DLJ
    0.37
    BtnPanel
    0.37
     Myself
    0.35
     রায়
    0.35
    询
    0.34
    egrave
    0.33
    ITOR
    0.33
    POSITIVE LOGITS
    ریشن
    0.52
    СК
    0.48
     Hark
    0.44
     replicating
    0.41
     lark
    0.39
     Lamin
    0.39
    やっと
    0.39
    Near
    0.38
    సే
    0.38
    Radiation
    0.38
    Activations Density 0.001%

    No Known Activations