© 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. 161113
    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
    t
    1.67
    li
    1.43
    ри
    1.13
    d
    1.13
    le
    1.12
    l
    1.11
    ı
    1.06
    т
    1.04
    ל
    1.04
    g
    1.02
    POSITIVE LOGITS
    2
    0.91
    }(
    0.84
    譴
    0.81
    ()
    0.78
    Bs
    0.77
    теля
    0.76
    4
    0.74
     طور
    0.73
    Aud
    0.73
     you
    0.72
    Activations Density 0.000%

    No Known Activations