© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58108
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ONLY
    0.40
     ONLY
    0.39
     keep
    0.38
     refere
    0.38
     Kyrgyz
    0.37
     Keeps
    0.36
    凈
    0.35
    킵
    0.35
     meant
    0.34
     रखेंगे
    0.34
    POSITIVE LOGITS
     all
    0.61
     tất
    0.56
     semua
    0.50
    all
    0.46
    still
    0.46
    arme
    0.45
     toate
    0.45
    ทั้งหมด
    0.44
     Semua
    0.44
     lahat
    0.44
    Activations Density 0.010%

    No Known Activations