© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4929
    Prev
    Next
    INDEX
    Explanations

    lists of concepts

    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
    to
    0.46
    the
    0.44
    outfile
    0.39
    on
    0.37
    iciar
    0.36
    posterior
    0.36
    ()=>{
    0.35
    même
    0.35
    ဦ
    0.35
    nt
    0.34
    POSITIVE LOGITS
    ى
    0.44
    ි
    0.37
    ة
    0.37
     ت
    0.35
    uge
    0.34
    이
    0.33
    каў
    0.33
    殑
    0.32
     divorce
    0.32
    вичай
    0.31
    Activations Density 2.884%

    No Known Activations