© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22695
    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_56_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
     royal
    0.48
     Royal
    0.48
    royal
    0.46
    Royal
    0.44
    য়ো
    0.41
    йма
    0.40
    oare
    0.40
    皇
    0.40
     royalties
    0.39
     ہوں۔
    0.38
    POSITIVE LOGITS
    Nau
    0.38
    vy
    0.37
     vy
    0.36
    task
    0.35
     Vocational
    0.35
     ang
    0.33
    lus
    0.33
    Gesture
    0.33
     Puck
    0.33
    Vy
    0.33
    Activations Density 0.000%

    No Known Activations