© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    fraught with

    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
    ق
    0.30
    のが
    0.29
    𝖙
    0.28
    ০
    0.27
    िन्न
    0.27
    ता
    0.27
    lığını
    0.26
    halation
    0.26
     automaton
    0.26
    fitted
    0.26
    POSITIVE LOGITS
    ња
    0.27
     únicamente
    0.27
     legale
    0.26
    𝑜
    0.26
    ರಾ
    0.25
     почему
    0.25
     mea
    0.24
    šky
    0.24
     ходить
    0.24
     costit
    0.24
    Activations Density 0.395%

    No Known Activations