© 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. 31314
    Prev
    Next
    INDEX
    Explanations

    bonus, flag, win

    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
     주민
    0.37
     เพ
    0.37
    ਲੀ
    0.37
     afar
    0.37
     바
    0.36
    uries
    0.36
    ပြင်
    0.36
    newdata
    0.35
    狧
    0.35
     Hogwarts
    0.35
    POSITIVE LOGITS
     Bonus
    0.54
     bonus
    0.49
    bonus
    0.49
    Bonus
    0.48
     Flag
    0.47
    Flag
    0.45
    flags
    0.43
     BONUS
    0.43
     flag
    0.42
     flags
    0.42
    Activations Density 0.133%

    No Known Activations