© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49640
    Prev
    Next
    INDEX
    Explanations

    s feelings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fontWeight
    0.46
    眉头
    0.45
    ameron
    0.43
    འ
    0.41
     両
    0.39
    栯
    0.38
    屶
    0.37
     hulp
    0.37
    alez
    0.37
    এস
    0.36
    POSITIVE LOGITS
     sensations
    0.79
     sensation
    0.78
     sø
    0.74
     sadness
    0.73
     satisfaction
    0.72
     sanctuary
    0.72
     س
    0.71
     serenity
    0.71
     są
    0.71
     sensational
    0.71
    Activations Density 0.115%

    No Known Activations