© 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. 108562
    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
     for
    1.51
    ור
    1.07
     einen
    0.90
     institu
    0.86
    ות
    0.86
    한
    0.85
     obten
    0.83
     carbure
    0.83
    ü
    0.82
     contamin
    0.82
    POSITIVE LOGITS
    t
    1.97
    al
    1.45
    b
    1.12
    v
    1.11
    ar
    1.09
    بة
    1.09
    act
    1.08
    y
    1.08
    mi
    1.06
    ai
    1.05
    Activations Density 0.000%

    No Known Activations