© 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. 241329
    Prev
    Next
    INDEX
    Explanations

    differentiable mathematical versatile

    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
    বিহার
    0.38
    lá
    0.37
    ốp
    0.36
    ',{
    0.36
     उपकरणों
    0.36
    嬛
    0.35
    conditionals
    0.35
    Signing
    0.34
    缟
    0.34
     장면
    0.34
    POSITIVE LOGITS
     cic
    0.38
    椿
    0.37
     Cic
    0.36
     waveform
    0.35
     Ritual
    0.35
     estima
    0.35
    国民
    0.34
     numerical
    0.34
     నెల
    0.34
     wave
    0.34
    Activations Density 0.000%

    No Known Activations