© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210049
    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_10_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
    𝖙
    0.55
    ؘ
    0.55
    .。
    0.53
    ('/:
    0.53
    ِّف
    0.52
    𝙉
    0.52
    ’।
    0.52
    ̣t
    0.52
    𝟎
    0.51
    Ϟ
    0.51
    POSITIVE LOGITS
    0.59
     grammar
    0.55
    Land
    0.45
    ian
    0.44
     Supreme
    0.44
     vic
    0.44
     principle
    0.43
     bell
    0.43
     eup
    0.42
     seed
    0.42
    Activations Density 0.000%

    No Known Activations