© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28076
    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
    </h4>
    0.52
    getInput
    0.50
    必要な
    0.49
    idora
    0.49
    ר
    0.48
    BSData
    0.48
    CollectedField
    0.45
    nameSort
    0.45
    ்க்கு
    0.45
     saga
    0.44
    POSITIVE LOGITS
    تب
    0.59
    tanggal
    0.50
    veratrol
    0.49
     pausing
    0.48
    hydrox
    0.48
    deoxy
    0.47
    té
    0.47
    ž
    0.47
     unanticipated
    0.46
     supplementation
    0.46
    Activations Density 0.000%

    No Known Activations