© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228976
    Prev
    Next
    INDEX
    Explanations

    it's okay to feel

    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_6_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
    o
    1.02
    ta
    0.90
    m
    0.89
    tes
    0.89
    ن
    0.89
    tochy
    0.85
    न
    0.84
    tae
    0.83
    th
    0.82
    triangle
    0.81
    POSITIVE LOGITS
    י
    0.92
     cui
    0.86
     crown
    0.84
     spine
    0.84
     optimizer
    0.83
     klasy
    0.83
     roof
    0.82
    χει
    0.82
    રી
    0.80
     hand
    0.79
    Activations Density 0.001%

    No Known Activations