© 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. 39462
    Prev
    Next
    INDEX
    Explanations

    scientific notation

    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
     sandstone
    0.35
    닉
    0.35
     Nec
    0.34
     rozp
    0.34
     هت
    0.33
     जल्
    0.33
    etva
    0.33
    -)
    0.32
     reaper
    0.32
     scented
    0.32
    POSITIVE LOGITS
    Ꮟ
    0.39
     .^{
    0.38
     beiden
    0.38
    Arrows
    0.37
     Старки
    0.36
     diyor
    0.35
    ellem
    0.35
     резко
    0.35
     exposição
    0.34
    सेन
    0.34
    Activations Density 0.003%

    No Known Activations