© 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. 175552
    Prev
    Next
    INDEX
    Explanations

    variable declaration keywords (const, let, local)

    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
    irió
    0.45
     trưởng
    0.43
     değil
    0.42
    ר
    0.41
    oniazid
    0.41
    urches
    0.41
     Vitória
    0.40
    ரி
    0.39
    лив
    0.39
     ފ
    0.39
    POSITIVE LOGITS
     archi
    0.46
     Backend
    0.44
    ×
    0.43
     backend
    0.43
     intend
    0.40
     nesting
    0.40
     lease
    0.39
     است
    0.39
    स्ति
    0.39
     look
    0.38
    Activations Density 0.001%

    No Known Activations