© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216104
    Prev
    Next
    INDEX
    Explanations

    by

    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_16_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
     doble
    0.53
    تم
    0.52
    阿
    0.51
    뜸
    0.49
     golpe
    0.48
    يء
    0.48
    ്രീ
    0.47
    மண
    0.47
    둠
    0.47
     ucc
    0.46
    POSITIVE LOGITS
     ज्वाइन
    0.48
     Analysts
    0.46
     Dijk
    0.46
     wygląd
    0.45
     passports
    0.45
     Nagar
    0.45
    Le
    0.44
    Skirt
    0.44
     Haq
    0.43
     Fahrzeuge
    0.43
    Activations Density 0.000%

    No Known Activations