© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202232
    Prev
    Next
    INDEX
    Explanations

    interests, activities, and goals

    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
     for
    0.95
    辎
    0.86
     coinciding
    0.81
    િ
    0.80
     discouraged
    0.79
    ف
    0.78
     ي
    0.78
    いました
    0.77
     pregunt
    0.77
     лоша
    0.77
    POSITIVE LOGITS
    (
    0.93
    :
    0.89
    SU
    0.88
    TableView
    0.84
    Sur
    0.82
    Corp
    0.82
    Neo
    0.81
    SERVER
    0.79
    Tact
    0.78
    ’
    0.78
    Activations Density 0.077%

    No Known Activations