© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233774
    Prev
    Next
    INDEX
    Explanations

    don't touch anything

    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_32_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
    ActionButton
    0.41
    ForegroundColor
    0.41
    触摸
    0.37
    onTouch
    0.37
    抚
    0.37
     OPERATION
    0.37
    伤
    0.37
    地上
    0.36
    Touchable
    0.36
     Touching
    0.36
    POSITIVE LOGITS
     requer
    0.39
     req
    0.38
     requis
    0.37
    req
    0.36
     requires
    0.36
     unpaid
    0.36
    ché
    0.36
     barbar
    0.35
     crucial
    0.35
    chard
    0.35
    Activations Density 0.003%

    No Known Activations