© 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. 47262
    Prev
    Next
    INDEX
    Explanations

    spin on

    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
    ing
    1.03
    as
    0.99
    l
    0.88
    ad
    0.83
    us
    0.81
    m
    0.80
    ah
    0.80
    t
    0.79
    to
    0.79
    r
    0.78
    POSITIVE LOGITS
    ↵
    0.66
    <0xA8>
    0.63
    <0xAA>
    0.61
    CodeableConcept
    0.60
    dokkaHtml
    0.60
     ей
    0.59
     исследование
    0.58
     但
    0.57
     сын
    0.57
    chette
    0.56
    Activations Density 0.021%

    No Known Activations