© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99769
    Prev
    Next
    INDEX
    Explanations

    `--v 5` parameters

    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_14_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
     of
    0.52
    די
    0.50
    x
    0.49
    מ
    0.49
    xE
    0.48
     خبرنگ
    0.46
    ד
    0.46
    烃
    0.45
     as
    0.45
    רה
    0.45
    POSITIVE LOGITS
    viel
    0.57
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.55
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.55
    amal
    0.55
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.52
    ackel
    0.52
    ↵↵↵↵↵↵↵↵↵↵
    0.51
     ConcurrentTask
    0.50
    lovepoetry
    0.50
    irian
    0.50
    Activations Density 0.003%

    No Known Activations