© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38886
    Prev
    Next
    INDEX
    Explanations

    increasing measures

    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
     esclare
    0.41
     çoc
    0.39
    zości
    0.36
     caver
    0.35
     बरत
    0.35
    爻
    0.35
     حاجات
    0.34
    நாய
    0.34
     Barbosa
    0.34
    aranth
    0.34
    POSITIVE LOGITS
    infinite
    0.43
     মার্ক
    0.36
     Rial
    0.35
     D
    0.35
    Marker
    0.34
     Produ
    0.33
     Tape
    0.33
     sliders
    0.33
    sliders
    0.33
     Infinite
    0.33
    Activations Density 0.001%

    No Known Activations