© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61196
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    و
    1.92
    ي
    1.88
    m
    1.56
    i
    1.54
    t
    1.44
    p
    1.26
    м
    1.24
    en
    1.21
     on
    1.17
    ا
    1.13
    POSITIVE LOGITS
    ந்து
    1.06
    سازی
    1.01
    주시
    0.97
    ۰
    0.96
     niềm
    0.96
    ین
    0.93
    ,
    0.90
     ولی
    0.88
     tục
    0.87
    ,’
    0.87
    Activations Density 0.000%

    No Known Activations