© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27326
    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_40_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
     ফুটবল
    0.41
     mengirim
    0.39
     Greenhouse
    0.39
    ㈤
    0.38
    itamins
    0.38
    Sending
    0.37
    uties
    0.37
    囝
    0.37
     फुटबॉल
    0.36
     numberOf
    0.36
    POSITIVE LOGITS
    Cabe
    0.41
    CAB
    0.38
     ಸು
    0.38
    俥
    0.37
    勧
    0.36
    сия
    0.36
     Cabrera
    0.36
     Rett
    0.34
    cabinet
    0.34
    ('').
    0.34
    Activations Density 0.000%

    No Known Activations