© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89217
    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_60_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
     गण
    0.38
     상
    0.36
     እን
    0.35
     ওর
    0.35
     생각
    0.35
     likely
    0.34
     बनने
    0.34
    rylic
    0.34
     risques
    0.34
     ее
    0.33
    POSITIVE LOGITS
     King
    1.72
    King
    1.62
     king
    1.52
     KING
    1.27
    king
    1.20
     किंग
    1.19
    KING
    1.01
     короля
    0.93
    킹
    0.93
    キング
    0.92
    Activations Density 0.035%

    No Known Activations