© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173019
    Prev
    Next
    INDEX
    Explanations

    up/down percentages

    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
    itude
    0.30
     delicate
    0.30
    cz
    0.29
    /
    0.29
    os
    0.28
    te
    0.28
    eli
    0.28
    us
    0.28
    umed
    0.28
    ound
    0.28
    POSITIVE LOGITS
     عرص
    0.32
    ケル
    0.31
     ditth
    0.31
    ᾷ
    0.30
     địa
    0.29
     쇼
    0.29
     क्षेत्रों
    0.29
    लेरिया
    0.29
     νη
    0.29
    琇
    0.29
    Activations Density 0.001%

    No Known Activations