© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137172
    Prev
    Next
    INDEX
    Explanations

    expenditure categories

    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
    easeInOut
    0.41
    omez
    0.38
     useContext
    0.38
     horsepower
    0.37
    ান্তি
    0.37
    ဆိုင်
    0.37
    杖
    0.36
    correctAns
    0.35
     IUE
    0.35
    andez
    0.34
    POSITIVE LOGITS
     食
    0.46
     народ
    0.43
    濠
    0.42
     Bour
    0.40
     ఆహ
    0.37
    밥
    0.37
     নিশ্চ
    0.37
    PLC
    0.37
    yg
    0.36
     darkened
    0.36
    Activations Density 0.001%

    No Known Activations