© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11283
    Prev
    Next
    INDEX
    Explanations

    reach goals or destinations

    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_40_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
     out
    0.57
    out
    0.55
    岕
    0.44
    OUT
    0.43
    เค
    0.43
    出し
    0.42
     Out
    0.42
    アウト
    0.42
     বেরিয়ে
    0.42
    Out
    0.40
    POSITIVE LOGITS
     slideshow
    0.40
     BI
    0.38
    bred
    0.38
    rna
    0.37
    maria
    0.36
    isms
    0.35
    na
    0.35
    翘
    0.35
     implementations
    0.35
     Stück
    0.35
    Activations Density 0.017%

    No Known Activations