© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210478
    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_20_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
    يمق
    0.57
    a
    0.57
    n
    0.50
    c
    0.49
    ار
    0.48
    بر
    0.48
    Br
    0.47
    br
    0.47
     loyal
    0.46
    P
    0.45
    POSITIVE LOGITS
    驪
    0.50
     daisies
    0.49
    岘
    0.48
    erais
    0.47
    }"),
    0.47
     আল্লাহর
    0.46
    葱
    0.46
     thánh
    0.45
    ূল
    0.44
     fiancé
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.