© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197223
    Prev
    Next
    INDEX
    Explanations

    google maps url

    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_26_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
    കസ
    0.46
     çi
    0.41
    ţional
    0.41
    jetas
    0.41
    𒀝
    0.40
     irre
    0.40
     Уен
    0.40
    isk
    0.40
     Ueda
    0.40
    acent
    0.39
    POSITIVE LOGITS
    וף
    0.47
     berhasil
    0.47
    どちら
    0.44
    นี่
    0.44
     dispel
    0.43
    かり
    0.43
    ⌜
    0.43
     פר
    0.42
    💎
    0.42
    겠습니다
    0.42
    Activations Density 0.000%

    No Known Activations