© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201126
    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_6_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
     a
    1.23
    am
    1.22
    en
    1.13
    on
    1.08
    W
    1.06
    od
    1.05
    K
    1.05
    J
    1.05
    ed
    1.04
    ad
    1.03
    POSITIVE LOGITS
    ни
    1.13
    ﺀ
    0.94
    т
    0.93
    ان
    0.90
    ж
    0.89
    ین
    0.89
    лно
    0.85
    ного
    0.83
    ين
    0.83
    ANE
    0.82
    Activations Density 0.000%

    No Known Activations