© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215764
    Prev
    Next
    INDEX
    Explanations

    say -

    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_47_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
    Cul
    0.42
    чению
    0.40
     घेतला
    0.38
    Numbers
    0.36
    Principal
    0.36
    _%
    0.35
    ۴
    0.35
    స్తు
    0.35
    ільки
    0.35
    icznych
    0.35
    POSITIVE LOGITS
    瘢
    0.41
    呦
    0.40
    निश्
    0.39
     हंसी
    0.38
    askar
    0.37
    currentSprite
    0.37
     Sterile
    0.37
     histologic
    0.36
    ayt
    0.36
     aeros
    0.35
    Activations Density 0.013%

    No Known Activations