© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103889
    Prev
    Next
    INDEX
    Explanations

    cash back rewards, cards, apps

    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_1_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
    j
    1.30
    z
    1.08
    st
    0.99
    i
    0.97
     rimane
    0.96
    ל
    0.95
    w
    0.93
    মূলক
    0.89
    joe
    0.89
    r
    0.88
    POSITIVE LOGITS
     is
    1.31
    s
    1.16
    ์
    1.11
    다
    1.05
    스
    1.02
    ки
    0.92
    ங்க
    0.92
    ง
    0.91
    를
    0.91
    ุ
    0.91
    Activations Density 0.002%

    No Known Activations