© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53961
    Prev
    Next
    INDEX
    Explanations

    half of

    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_30_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
    תיים
    0.35
     gắng
    0.35
     利
    0.35
     insofar
    0.34
     forem
    0.34
    ွေ
    0.34
    ጕ
    0.34
    genheim
    0.33
     tangential
    0.33
     siden
    0.33
    POSITIVE LOGITS
    ڙ
    0.42
     پنج
    0.39
    гла
    0.38
    再び
    0.36
     다섯
    0.36
     tekr
    0.36
     പിന്നീ
    0.36
     Peb
    0.36
    bestand
    0.34
     તરી
    0.34
    Activations Density 0.003%

    No Known Activations