© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31825
    Prev
    Next
    INDEX
    Explanations

    entry= or type:

    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
    炅
    0.37
     forth
    0.36
     subscriptions
    0.35
     Butterworth
    0.35
    قوق
    0.35
    ::*;
    0.34
    Intercept
    0.34
     pictureBox
    0.34
     FEED
    0.34
    setFillColor
    0.34
    POSITIVE LOGITS
     vengo
    0.39
    iasa
    0.39
     tuyến
    0.38
    Hashing
    0.37
    謎
    0.37
     vértice
    0.36
    টাল
    0.36
    ysteem
    0.36
    Never
    0.36
     Dancing
    0.36
    Activations Density 0.000%

    No Known Activations