© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49355
    Prev
    Next
    INDEX
    Explanations

    thinkers' names

    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_55_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
    loot
    0.45
     Shakespeare
    0.44
     Napoleon
    0.43
     Einstein
    0.42
     Goethe
    0.42
    ]["
    0.42
     Mozart
    0.42
     রবীন্দ্রনাথ
    0.42
     Aristotle
    0.41
     Napole
    0.41
    POSITIVE LOGITS
    iological
    0.42
    arbeiten
    0.41
    髅
    0.41
    ี่ยม
    0.39
    ian
    0.38
     himself
    0.38
     çalışmaları
    0.37
    ęż
    0.37
    ческом
    0.37
    كرة
    0.37
    Activations Density 0.005%

    No Known Activations