© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205212
    Prev
    Next
    INDEX
    Explanations

    portfolio

    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_56_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
    ഞ്ഞെടു
    0.39
     एरिया
    0.37
     promising
    0.37
    arching
    0.35
    nu
    0.35
    ۥ
    0.34
    বেগ
    0.33
     Ў
    0.33
     Area
    0.33
    thag
    0.33
    POSITIVE LOGITS
     состав
    0.54
    Composition
    0.50
     composed
    0.49
     construction
    0.48
     composta
    0.48
     comprised
    0.48
     composto
    0.48
    Construction
    0.47
     constitué
    0.46
     составляют
    0.46
    Activations Density 0.002%

    No Known Activations