© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3185
    Prev
    Next
    INDEX
    Explanations

    thrifting, making, slicing dice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ية
    2.38
    ful
    1.89
     Архів
    1.81
    г
    1.62
    ز
    1.62
    ুৎ
    1.60
    hearted
    1.60
    ∖
    1.53
    ি
    1.52
    h
    1.51
    POSITIVE LOGITS
     matchups
    1.99
     glaube
    1.79
     lindos
    1.75
     clim
    1.70
     hate
    1.70
     vols
    1.69
     carat
    1.69
    ﯽ
    1.68
     investigación
    1.68
    isRunning
    1.66
    Activations Density 0.000%

    No Known Activations