© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26795
    Prev
    Next
    INDEX
    Explanations

    Text

    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_40_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
    private
    0.47
     Serm
    0.43
    㣩
    0.42
     serm
    0.40
     statistically
    0.38
     private
    0.38
     da
    0.37
    ᱕
    0.37
     statistical
    0.37
    Nomin
    0.37
    POSITIVE LOGITS
     صوت
    0.54
    เสียง
    0.46
     الصوت
    0.45
    の声
    0.44
    聲音
    0.44
    的声音
    0.42
     صدای
    0.41
     स्पी
    0.41
     zvuk
    0.41
    Voice
    0.40
    Activations Density 0.002%

    No Known Activations