© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206343
    Prev
    Next
    INDEX
    Explanations

    your business or personal projects

    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_20_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
    Synt
    0.29
    synt
    0.28
     nothing
    0.27
    nothing
    0.24
     awfully
    0.24
    oggling
    0.24
    igent
    0.24
    熊
    0.24
    learning
    0.24
     conco
    0.24
    POSITIVE LOGITS
    ຜ
    0.25
     agr
    0.25
    宽松
    0.24
     ¿
    0.24
     परीक्षाओं
    0.24
    受験
    0.23
    缆
    0.23
     ¡
    0.23
    行走
    0.23
     जिससे
    0.23
    Activations Density 0.006%

    No Known Activations