© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257236
    Prev
    Next
    INDEX
    Explanations

    sit commands

    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_22_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
    律师
    0.46
    𝓼
    0.46
     נישט
    0.45
    买了
    0.45
    楨
    0.44
    🉐
    0.44
     "=",
    0.43
    strdup
    0.42
    ൊന്നും
    0.41
     देशभर
    0.41
    POSITIVE LOGITS
     inhale
    0.45
     >
    0.40
     superseded
    0.40
     upgraded
    0.39
     ann
    0.39
     allem
    0.39
     modernized
    0.39
     gazing
    0.39
     inhal
    0.38
     isra
    0.38
    Activations Density 0.002%

    No Known Activations