© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3234
    Prev
    Next
    INDEX
    Explanations

    legal trials and charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     Challenge
    0.41
     Protein
    0.41
    锻
    0.40
     заго
    0.39
     Karm
    0.38
     CHALL
    0.37
     नाते
    0.36
    칸
    0.36
     захворю
    0.36
     protein
    0.36
    POSITIVE LOGITS
     trial
    1.16
     Trial
    1.06
    Trial
    1.06
    trial
    0.96
     jury
    0.95
     trials
    0.89
     TRIAL
    0.89
    trials
    0.84
     Trials
    0.84
     Jury
    0.83
    Activations Density 0.058%

    No Known Activations