© 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. 175913
    Prev
    Next
    INDEX
    Explanations

    because the following explanation

    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
    ်
    0.33
    加拿
    0.31
     исче
    0.31
     डाउन
    0.31
     chapter
    0.31
     conversely
    0.30
     İstifadə
    0.30
    adero
    0.30
     desapare
    0.30
    关于
    0.30
    POSITIVE LOGITS
    Starter
    0.33
    েশ্বর
    0.33
    tochrome
    0.32
    亙
    0.31
    USB
    0.31
    Objective
    0.30
    routine
    0.29
    UKA
    0.29
    ρεί
    0.29
    撒
    0.29
    Activations Density 0.020%

    No Known Activations