© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149043
    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_23_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
    alignParent
    0.40
    marker
    0.38
    कल
    0.38
    જ
    0.38
    кансер
    0.38
    ソ
    0.38
    Би
    0.38
    ociation
    0.37
    归
    0.37
    心思
    0.37
    POSITIVE LOGITS
     Kollegen
    0.40
     భ
    0.39
     Burgen
    0.39
     DEC
    0.38
     Produ
    0.38
     Glück
    0.38
     क्रिप्टो
    0.38
     Kranken
    0.38
    ِينَ
    0.38
     schafft
    0.38
    Activations Density 0.000%

    No Known Activations