© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91348
    Prev
    Next
    INDEX
    Explanations

    express emotions

    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_60_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
    So
    0.46
    for
    0.46
    An
    0.43
    Over
    0.43
    Ш
    0.43
    For
    0.43
    Am
    0.42
    Ș
    0.42
    Special
    0.42
    Chill
    0.42
    POSITIVE LOGITS
     port
    0.68
     porta
    0.59
     Portraits
    0.54
     पोर्ट
    0.54
     produce
    0.52
     serve
    0.52
     build
    0.51
     handle
    0.51
     Ports
    0.50
     porto
    0.50
    Activations Density 0.027%

    No Known Activations