© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42059
    Prev
    Next
    INDEX
    Explanations

    BLS certification

    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_3_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
    ő
    0.64
    дцать
    0.61
    والفقار
    0.57
    ukone
    0.55
    一颗
    0.55
     중요하다
    0.54
     تعمیر
    0.54
     이날
    0.54
    ERS
    0.53
    것도
    0.53
    POSITIVE LOGITS
    ↵
    0.86
     was
    0.84
    m
    0.81
    ди
    0.77
    it
    0.75
    ف
    0.75
    ud
    0.74
     série
    0.74
    f
    0.74
    ire
    0.73
    Activations Density 0.000%

    No Known Activations