© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193508
    Prev
    Next
    INDEX
    Explanations

    comfort

    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_27_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
    交代
    0.42
    SCUS
    0.38
    reactor
    0.36
     provoked
    0.36
     REACTOR
    0.35
    realistic
    0.33
    KOH
    0.33
    휙
    0.33
    Gren
    0.32
    RICH
    0.32
    POSITIVE LOGITS
     komfort
    0.44
     ventilation
    0.43
     sadness
    0.43
     attrezz
    0.41
     neum
    0.41
    arlama
    0.41
     sad
    0.41
     आरामदायक
    0.41
    狽
    0.41
    ница
    0.40
    Activations Density 0.001%

    No Known Activations