© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137192
    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_12_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
    et
    1.01
    U
    0.64
    ub
    0.61
    ot
    0.59
    em
    0.58
    ib
    0.57
    ುವುದಿಲ್ಲ
    0.57
    etku
    0.57
    iv
    0.55
    R
    0.55
    POSITIVE LOGITS
     subsidi
    0.57
     speechSynthesis
    0.56
     subj
    0.54
     διαδικ
    0.54
     asignatura
    0.53
     facilita
    0.53
    粌
    0.52
     decad
    0.51
     könne
    0.50
     bądź
    0.50
    Activations Density 0.000%

    No Known Activations