© 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. 206330
    Prev
    Next
    INDEX
    Explanations

    physics and specific entities

    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
    ambiental
    0.40
    besiege
    0.40
    书
    0.38
     به
    0.38
    环保
    0.37
    languageTag
    0.37
     edn
    0.37
    職場
    0.36
     venerable
    0.36
    <0x8F>
    0.36
    POSITIVE LOGITS
     नहीं
    0.46
     نہیں
    0.46
    ễm
    0.46
    não
    0.43
     หยุด
    0.41
     nimmt
    0.41
    ımı
    0.40
    หยุด
    0.40
     nahil
    0.40
     యే
    0.39
    Activations Density 0.000%

    No Known Activations