© 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. 36223
    Prev
    Next
    INDEX
    Explanations

    commenting on posts

    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_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
     Hilary
    0.41
    揾
    0.39
     MARTIN
    0.37
    쿨
    0.37
    찰
    0.36
     школе
    0.36
     Tis
    0.35
    Zer
    0.35
    プリ
    0.35
     звер
    0.35
    POSITIVE LOGITS
     Facebook
    0.38
     photograph
    0.37
     conquer
    0.36
     পোস্টে
    0.36
     conquered
    0.35
     BlogPost
    0.35
     comment
    0.35
     每
    0.35
     article
    0.34
     youtube
    0.34
    Activations Density 0.050%

    No Known Activations