© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61809
    Prev
    Next
    INDEX
    Explanations

    python code

    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_59_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
     huv
    0.44
    绡
    0.36
     curvil
    0.36
     мою
    0.35
    觜
    0.35
     haupt
    0.34
    淋
    0.34
     వివ
    0.33
    طلاع
    0.33
    uacao
    0.33
    POSITIVE LOGITS
    weight
    0.39
    %>
    0.37
    рей
    0.37
    receive
    0.36
     ऊंची
    0.36
    lob
    0.35
    accept
    0.35
     මෙ
    0.34
     &_
    0.34
    thouse
    0.34
    Activations Density 0.014%

    No Known Activations