© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196370
    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_9_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
    र
    0.53
    нак
    0.47
     వ
    0.47
    ね
    0.47
     во
    0.46
    ை
    0.46
     script
    0.46
     recipe
    0.46
    Ꮙ
    0.46
     как
    0.45
    POSITIVE LOGITS
    받
    0.52
    ت
    0.51
     Tarot
    0.49
     Treasures
    0.48
     Trivia
    0.48
     Scarborough
    0.47
     Sebuah
    0.47
     Tutto
    0.47
     Sees
    0.47
    لح
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.