© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37264
    Prev
    Next
    INDEX
    Explanations

    say "_"

    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_57_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
    ionali
    0.36
     fermion
    0.36
    ของเรา
    0.36
    庿
    0.36
    唕
    0.35
     Tandy
    0.34
     הער
    0.34
    頖
    0.34
     هە
    0.33
     SCT
    0.33
    POSITIVE LOGITS
    ческа
    0.35
    <sub>
    0.34
    cases
    0.34
    چان
    0.34
    cutting
    0.34
     før
    0.33
    pais
    0.33
    zilla
    0.33
    зора
    0.33
    зок
    0.33
    Activations Density 0.017%

    No Known Activations