© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139186
    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
     Projek
    0.47
    S
    0.46
     Penn
    0.46
     Mik
    0.46
    Akt
    0.45
    Rae
    0.43
    ää
    0.43
     Raw
    0.42
    Ä
    0.42
    Jan
    0.42
    POSITIVE LOGITS
     alcun
    0.51
     relinqu
    0.51
     می
    0.50
     nomad
    0.50
     ecclesiastical
    0.49
     шести
    0.49
    ೮
    0.49
     croche
    0.48
     jovens
    0.48
     inflatable
    0.48
    Activations Density 0.000%

    No Known Activations