© 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. 3401
    Prev
    Next
    INDEX
    Explanations

    Re: Feature, Suggestion, Re:Zero, Application

    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
    要
    0.34
     suman
    0.34
    多家
    0.34
    तेक
    0.31
    一種
    0.31
     lamang
    0.31
    এবং
    0.31
     нача
    0.31
    s
    0.31
     dioxide
    0.31
    POSITIVE LOGITS
     kuasa
    0.30
    fashioned
    0.30
    পো
    0.30
    াগ
    0.29
    mene
    0.29
    barrel
    0.28
    tive
    0.28
    pox
    0.28
    posted
    0.27
    tellers
    0.27
    Activations Density 0.003%

    No Known Activations