© 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. 25254
    Prev
    Next
    INDEX
    Explanations

    include and function calls

    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
     detergent
    0.81
     anhydrous
    0.72
    o
    0.70
    os
    0.68
    ET
    0.68
    t
    0.66
    es
    0.65
    ’
    0.64
    ه‌ای
    0.62
    או
    0.61
    POSITIVE LOGITS
    फ़
    0.68
     बहुत
    0.66
    cantidad
    0.66
     जहाँ
    0.64
    𝙘
    0.63
     प्रभावों
    0.61
    xb
    0.60
     प्रार
    0.60
    picture
    0.59
     पॉपुलर
    0.59
    Activations Density 0.004%

    No Known Activations