© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 173641
    Prev
    Next
    INDEX
    Explanations

    kilometers, miles, reflux, burning

    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
    肅
    0.17
    鿌
    0.17
     scopo
    0.17
     производ
    0.17
     salva
    0.17
    㿟
    0.17
     PRODU
    0.17
     北
    0.17
     પોતા
    0.17
     생산
    0.16
    POSITIVE LOGITS
     plague
    0.18
     tightness
    0.18
    ्यर
    0.17
     callBack
    0.17
     threaten
    0.16
    bur
    0.16
     ryzy
    0.16
    nonce
    0.16
    ahui
    0.15
     loading
    0.15
    Activations Density 0.001%

    No Known Activations