© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57349
    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_11_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
    0.91
    er
    0.68
    f
    0.62
    c
    0.61
    l
    0.60
    s
    0.58
     Their
    0.56
    r
    0.55
    orphan
    0.54
     их
    0.53
    POSITIVE LOGITS
    ۹
    0.55
    Ꮠ
    0.52
    وى
    0.52
     설계
    0.52
    ської
    0.51
    ༞
    0.51
    မူ
    0.51
     avem
    0.49
     ಕಾಂಗ್ರೆ
    0.48
    嘬
    0.47
    Activations Density 0.000%

    No Known Activations