© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126903
    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_37_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
     aldı
    0.43
    ativistic
    0.41
    啕
    0.41
    柘
    0.40
    威
    0.39
    טא
    0.38
     সঞ্জীবনী
    0.38
    ক্ট
    0.38
     վ
    0.38
     simplices
    0.38
    POSITIVE LOGITS
    Disclosure
    0.39
     traceable
    0.39
    imagine
    0.38
    Lead
    0.37
     bilin
    0.35
     неизвест
    0.35
    disclosure
    0.34
    BW
    0.34
    umbre
    0.34
    MOT
    0.33
    Activations Density 0.000%

    No Known Activations