© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166850
    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_31_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
    名前
    0.39
    ='';
    0.36
    secrets
    0.35
    扈
    0.35
     todays
    0.35
    weis
    0.34
     акчага
    0.34
     همه
    0.34
    wehr
    0.33
    ''_
    0.33
    POSITIVE LOGITS
     Patient
    0.38
     Cafe
    0.37
    Bootstrap
    0.36
     সপ্ত
    0.36
     Cake
    0.35
     low
    0.35
     簡単
    0.35
     Qd
    0.35
     ब
    0.34
     displays
    0.34
    Activations Density 0.000%

    No Known Activations