© 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. 205540
    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
    도
    1.16
    ও
    0.91
    0.89
     \
    0.87
    نی
    0.87
    stimulating
    0.87
    mann
    0.82
    Metering
    0.82
    Q
    0.82
    Aging
    0.81
    POSITIVE LOGITS
    at
    1.64
    as
    1.54
    on
    1.34
    و
    1.28
    ي
    1.16
    ва
    1.15
    наче
    1.15
    ו
    1.14
    كبر
    1.08
    是个
    1.05
    Activations Density 0.000%

    No Known Activations