© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170711
    Prev
    Next
    INDEX
    Explanations

    buildup

    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_20_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
     ιδια
    0.46
     armor
    0.44
     methylene
    0.44
     blades
    0.44
    وا
    0.43
    랜
    0.43
    智能
    0.43
     dilemmas
    0.43
    const
    0.42
    typedef
    0.42
    POSITIVE LOGITS
     ausschließlich
    0.52
     nisid
    0.47
     Änderung
    0.46
    രംഭ
    0.45
    喺
    0.45
    ruciating
    0.45
     двух
    0.45
     ಎರಡ
    0.45
     gtag
    0.44
     esclusivamente
    0.44
    Activations Density 0.001%

    No Known Activations