© 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-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140623
    Prev
    Next
    INDEX
    Explanations

    coach

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    órico
    0.44
    嵬
    0.42
     Consulta
    0.40
    掫
    0.39
    EventType
    0.39
    consulta
    0.39
    ற்று
    0.38
    疵
    0.38
    öv
    0.38
    psia
    0.37
    POSITIVE LOGITS
    ([{
    0.43
     {
    0.42
     kat
    0.41
     debit
    0.38
    {[
    0.37
     phases
    0.36
    [(
    0.36
     Koc
    0.36
     sol
    0.35
     Alh
    0.35
    Activations Density 0.002%

    No Known Activations