© 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. 49505
    Prev
    Next
    INDEX
    Explanations

    strengthen, reform, provide

    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
     cứu
    0.41
     ключ
    0.40
    収
    0.39
    紐
    0.38
     ravel
    0.37
    サービス
    0.36
     Voting
    0.36
    救
    0.35
     তেল
    0.35
     तेल
    0.35
    POSITIVE LOGITS
    ippi
    0.38
     surgi
    0.38
    ন্নত
    0.37
     tratta
    0.37
    ینی
    0.36
    abca
    0.36
    braska
    0.36
    寐
    0.35
     coleg
    0.35
     लंबा
    0.34
    Activations Density 0.006%

    No Known Activations