© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50016
    Prev
    Next
    INDEX
    Explanations

    string or cord

    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
    0
    0.29
    of
    0.24
    ہ
    0.24
     xhrObj
    0.24
    <0x80>
    0.23
     Angaben
    0.22
    𝟬
    0.22
    ０
    0.21
     Đối
    0.21
     ০
    0.21
    POSITIVE LOGITS
    ↵
    0.25
    e
    0.24
    เป็น
    0.23
     convenient
    0.22
    ક્તિ
    0.22
     pathway
    0.21
     convoc
    0.21
     considerate
    0.21
     routes
    0.21
     cursory
    0.21
    Activations Density 0.013%

    No Known Activations