© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43179
    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_22_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
    嚣
    0.52
    estado
    0.49
    стью
    0.49
    өрд
    0.48
    ٦
    0.46
    χω
    0.46
     estampado
    0.46
    á
    0.45
    ोर
    0.45
    isão
    0.45
    POSITIVE LOGITS
    鄀
    0.46
     nécess
    0.45
     السيارة
    0.45
     ഏറെ
    0.45
     требуют
    0.44
    रिक्
    0.43
     باس
    0.43
     ഒരിക്ക
    0.43
    ("#
    0.42
    我们需要
    0.42
    Activations Density 0.000%

    No Known Activations