© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26777
    Prev
    Next
    INDEX
    Explanations

    "I" or "Please" followed by a verb

    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_10_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
     angiography
    0.29
     universitet
    0.27
    ṟ
    0.27
     université
    0.26
     I
    0.25
     eyewitness
    0.25
     abbat
    0.24
     WITH
    0.24
     cyborg
    0.24
    กรณ์
    0.24
    POSITIVE LOGITS
    ز
    0.26
    ↵↵
    0.24
    st
    0.23
    سط
    0.23
    ната
    0.22
    ו
    0.22
    χ
    0.22
    و
    0.21
    وع
    0.21
    يد
    0.21
    Activations Density 0.068%

    No Known Activations