© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206022
    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_20_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
     श्रद्धाल
    0.45
    attaa
    0.45
    Socket
    0.44
    utors
    0.44
     สํา
    0.44
    িয়ার
    0.44
    রাদ
    0.43
    秥
    0.43
     orgánica
    0.43
    ार्थी
    0.42
    POSITIVE LOGITS
     craziness
    0.45
     crazy
    0.45
     everytime
    0.44
     brute
    0.42
     catastrophes
    0.42
     ทำให้
    0.40
     uncontrolled
    0.40
     loads
    0.39
     দেখো
    0.39
     BC
    0.38
    Activations Density 0.000%

    No Known Activations