© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30047
    Prev
    Next
    INDEX
    Explanations

    summarize this article

    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_7_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
     сете
    0.73
     to
    0.73
    乆
    0.70
    לות
    0.70
     ponto
    0.69
     argu
    0.68
     cerv
    0.67
     restring
    0.66
     legible
    0.66
     adiab
    0.66
    POSITIVE LOGITS
    f
    1.61
    ک
    1.50
    ik
    1.47
    j
    1.42
    im
    1.37
    ad
    1.34
    k
    1.34
    ag
    1.31
    an
    1.30
    v
    1.27
    Activations Density 0.002%

    No Known Activations