© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4969
    Prev
    Next
    INDEX
    Explanations

    keys, passwords, tools, and objects

    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_3_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
    ्स
    0.41
    ients
    0.38
    क
    0.38
    ்
    0.37
    UARY
    0.36
    至於
    0.35
    as
    0.35
    кий
    0.34
    at
    0.34
    xiety
    0.33
    POSITIVE LOGITS
    ets
    0.33
    له
    0.32
     únicas
    0.32
     straordin
    0.31
     slechts
    0.30
     graus
    0.29
    عنوان
    0.29
    钬
    0.29
     zabaw
    0.29
     inizi
    0.29
    Activations Density 0.565%

    No Known Activations