© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176524
    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_24_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
    蔥
    0.50
     UCC
    0.49
     conferring
    0.49
     convening
    0.49
    城
    0.46
    菇
    0.46
    ায়ণ
    0.46
    ាវ
    0.46
    庖
    0.45
    Ꮘ
    0.45
    POSITIVE LOGITS
    ate
    0.45
    ines
    0.45
    anc
    0.44
    मध्ये
    0.44
     フリー
    0.43
    uke
    0.43
    ව
    0.43
    jev
    0.43
     ተመሳሳይ
    0.43
    ase
    0.42
    Activations Density 0.000%

    No Known Activations