© 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. 121443
    Prev
    Next
    INDEX
    Explanations

    parts of words ending in 'ar', 'art', 'izing'

    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
     Darstellung
    0.70
    t
    0.70
    0.70
     curator
    0.67
     département
    0.65
     že
    0.64
     decât
    0.63
    tım
    0.61
    <0x93>
    0.61
     totalled
    0.61
    POSITIVE LOGITS
    0
    0.95
    er
    0.90
    其他
    0.84
    ین
    0.77
    mill
    0.77
    𝟬
    0.76
    km
    0.75
    vy
    0.73
    ck
    0.73
    vi
    0.72
    Activations Density 0.000%

    No Known Activations