© 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. 206229
    Prev
    Next
    INDEX
    Explanations

    chest pain or muscles

    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
    z
    0.22
     மன்னி
    0.20
    fried
    0.19
    mile
    0.19
    dad
    0.19
    life
    0.19
    swith
    0.19
    f
    0.18
    р
    0.18
    seventh
    0.18
    POSITIVE LOGITS
    ที่
    0.21
    ﻢ
    0.19
    ם
    0.19
    시아
    0.19
    נ
    0.19
    גו
    0.18
     glaring
    0.18
    വരെ
    0.18
     aurait
    0.18
     dalej
    0.17
    Activations Density 0.007%

    No Known Activations