© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30199
    Prev
    Next
    INDEX
    Explanations

    climate change

    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_10_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
    مس
    0.36
    يس
    0.36
    يع
    0.34
    हित्य
    0.34
     Stunden
    0.33
    句話
    0.33
    ١
    0.32
    ស់
    0.32
    d
    0.32
    على
    0.32
    POSITIVE LOGITS
    숀
    0.41
     propaganda
    0.39
     कैटरीना
    0.38
     augment
    0.38
     confertim
    0.38
     conformal
    0.37
     censor
    0.36
     revolt
    0.36
    )(
    0.35
    fand
    0.35
    Activations Density 0.002%

    No Known Activations