© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45151
    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
     যথেষ্ট
    0.42
    Autowired
    0.42
     بیاکت
    0.40
     Automat
    0.40
    raud
    0.40
    兇
    0.40
    ინი
    0.39
     ያስፈል
    0.39
     Bureau
    0.39
     Zo
    0.39
    POSITIVE LOGITS
    garakan
    0.44
    щим
    0.43
    нология
    0.42
    ంథ
    0.42
     medios
    0.41
    nested
    0.41
    जम
    0.40
    <0x85>
    0.39
     leaks
    0.39
     creeping
    0.38
    Activations Density 0.000%

    No Known Activations