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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36233
    Prev
    Next
    INDEX
    Explanations

    brochure or broiler

    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_3_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
     in
    0.88
    س
    0.83
    ים
    0.81
     industri
    0.79
    د
    0.79
    de
    0.78
    ิน
    0.75
    在
    0.73
    جا
    0.72
    ول
    0.72
    POSITIVE LOGITS
    IY
    0.66
    Lar
    0.66
    o
    0.66
    matic
    0.64
    DOWN
    0.64
    Member
    0.63
    v
    0.63
    থাৎ
    0.62
    Powell
    0.62
    r
    0.62
    Activations Density 0.001%

    No Known Activations