© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117433
    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_27_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
    얼
    0.19
    ੋ
    0.17
    Fighting
    0.17
    Being
    0.16
    At
    0.16
    ieving
    0.16
    嘹
    0.16
    ー
    0.15
    Ꮧ
    0.15
    Despite
    0.15
    POSITIVE LOGITS
     volat
    0.19
     halibut
    0.17
     pháp
    0.17
     subscript
    0.17
     coords
    0.17
     utilizar
    0.17
     volatility
    0.16
     stabilize
    0.16
     pollinators
    0.16
     symbols
    0.16
    Activations Density 0.000%

    No Known Activations