© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126417
    Prev
    Next
    INDEX
    Explanations

    numbered lists and "how-to" guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    amos
    0.45
    oten
    0.38
    bezpie
    0.38
    ocie
    0.38
    悵
    0.38
     circuitry
    0.37
    istory
    0.36
    four
    0.36
    낵
    0.36
     cinq
    0.35
    POSITIVE LOGITS
     Ways
    0.40
     повто
    0.39
     menggel
    0.39
     Ideas
    0.38
     giết
    0.38
    들의
    0.37
     매
    0.36
     idées
    0.36
    ِس
    0.36
    RelativeLayout
    0.36
    Activations Density 0.001%

    No Known Activations