© 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. 25306
    Prev
    Next
    INDEX
    Explanations

    total + negative outcome

    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
    ی
    0.50
    т
    0.50
    ي
    0.48
    ни
    0.48
    ీ
    0.47
    ين
    0.47
    ச்
    0.45
    ت
    0.45
    years
    0.45
    ು
    0.44
    POSITIVE LOGITS
    .
    0.63
    :
    0.63
    7
    0.37
     GC
    0.37
    
    0.37
    และการ
    0.35
     webbrowser
    0.35
     foodservice
    0.35
     synt
    0.34
    2
    0.34
    Activations Density 0.002%

    No Known Activations