© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203103
    Prev
    Next
    INDEX
    Explanations

    device settings, startup, shutdown

    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_25_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
    γγελ
    0.41
     প্রভ
    0.40
     হবেন
    0.40
    шев
    0.40
    辺
    0.40
     범위
    0.39
    ሑ
    0.39
     lanceol
    0.38
    もので
    0.38
    ᱩ
    0.37
    POSITIVE LOGITS
     ja
    0.37
     fresca
    0.36
    aving
    0.35
     rs
    0.35
     và
    0.35
    Glu
    0.35
     ਅਤੇ
    0.35
     and
    0.34
     Emily
    0.34
     extracellular
    0.34
    Activations Density 0.000%

    No Known Activations