© 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. 45522
    Prev
    Next
    INDEX
    Explanations

    immediately following

    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
    us
    0.32
    िष्ट
    0.31
    t
    0.29
    on
    0.28
    ai
    0.28
    es
    0.26
    os
    0.26
    ez
    0.26
    izquierda
    0.25
    <0x86>
    0.25
    POSITIVE LOGITS
     ਪ
    0.30
    A
    0.27
     carousel
    0.26
     פ
    0.26
     र
    0.26
     induction
    0.25
    ד
    0.25
     ช
    0.25
     usefulness
    0.25
    น
    0.25
    Activations Density 0.012%

    No Known Activations