© 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. 49406
    Prev
    Next
    INDEX
    Explanations

    now, in time, at this moment

    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
     ahora
    0.35
     now
    0.35
    오늘은
    0.33
     이제
    0.33
     ಈಗ
    0.32
     secolo
    0.32
     এখন
    0.31
    즈
    0.31
     nowadays
    0.30
     இந்
    0.30
    POSITIVE LOGITS
     wards
    0.33
     tẩy
    0.33
     lainnya
    0.30
    சல்
    0.30
     word
    0.30
     словам
    0.30
     sparing
    0.29
    pite
    0.29
    atever
    0.29
     словами
    0.29
    Activations Density 0.006%

    No Known Activations