© 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. 26649
    Prev
    Next
    INDEX
    Explanations

    sensitivity and coupling

    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
     CEP
    0.38
     Generating
    0.37
    гене
    0.36
    Насе
    0.35
    로우
    0.35
     cep
    0.35
     انب
    0.35
    邺
    0.35
    CEP
    0.34
     Elapsed
    0.34
    POSITIVE LOGITS
     coupled
    0.62
     coupling
    0.53
     Coupled
    0.53
     couples
    0.50
    coupled
    0.49
     sensitivity
    0.47
    calibration
    0.47
    coupling
    0.45
     calibrate
    0.44
     Couples
    0.44
    Activations Density 0.051%

    No Known Activations