© 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. 195687
    Prev
    Next
    INDEX
    Explanations

    server setup

    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
    رد
    0.47
     liquors
    0.45
    𝚞
    0.41
    UserProg
    0.40
     patrones
    0.39
     voitures
    0.39
    ق
    0.39
    只限平日
    0.38
    рав
    0.38
     राहत
    0.38
    POSITIVE LOGITS
     Sentiment
    0.43
    ؕ
    0.41
     Silence
    0.39
     뭐가
    0.39
     Evidently
    0.39
     Modifier
    0.38
     Сколько
    0.38
     Vì
    0.38
     प्रबंधक
    0.38
     Sebab
    0.37
    Activations Density 0.000%

    No Known Activations