© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247012
    Prev
    Next
    INDEX
    Explanations

    DNS resolution issues

    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_40_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
    आख
    0.36
    UpdateButton
    0.35
    ON
    0.35
    贡
    0.35
    onyl
    0.33
     अद
    0.33
     ===========
    0.33
    最終
    0.33
    scrollTop
    0.33
    Thou
    0.33
    POSITIVE LOGITS
     promouvoir
    0.43
    etheus
    0.43
    ગે
    0.39
     baba
    0.38
     Baba
    0.38
     Foster
    0.37
     मानने
    0.37
     promover
    0.37
    ലൈ
    0.37
     fosters
    0.37
    Activations Density 0.001%

    No Known Activations