© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33395
    Prev
    Next
    INDEX
    Explanations

    warframe fighter series

    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
    Negative Logits
    >
    0.91
    ↵
    0.75
    >$
    0.65
    ות
    0.64
    ան
    0.57
    فك
    0.57
    說
    0.57
    ב
    0.57
    ید
    0.56
    ปี
    0.55
    POSITIVE LOGITS
    "।
    0.66
    bersome
    0.63
    O
    0.61
    description
    0.60
    i
    0.60
     описание
    0.57
     হইয়াছিলেন
    0.56
    ן
    0.56
    da
    0.56
    lessness
    0.56
    Activations Density 0.001%

    No Known Activations