© 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. 205344
    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
     puesta
    0.39
     उद
    0.38
    rots
    0.38
     compensatory
    0.36
     bereavement
    0.36
    䂙
    0.36
    补偿
    0.36
     vesting
    0.36
    れた
    0.36
     rot
    0.35
    POSITIVE LOGITS
    ))=\
    0.39
    ')),
    0.39
     сх
    0.38
     ක්‍ර
    0.38
    igarh
    0.38
     Zugriff
    0.38
    Tracker
    0.37
    )&&
    0.37
    ッコ
    0.37
    गुन
    0.37
    Activations Density 0.000%

    No Known Activations