© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260960
    Prev
    Next
    INDEX
    Explanations

    Keras, TensorFlow, CNTK

    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_5_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
    л
    1.51
    ע
    1.29
    कर
    1.27
    ة
    1.25
     as
    1.24
    س
    1.23
    ق
    1.21
    го
    1.17
    يت
    1.14
    '
    1.13
    POSITIVE LOGITS
    7
    1.26
     וא
    1.15
    8
    1.05
     אחד
    1.02
    6
    0.98
    SD
    0.98
     וה
    0.95
    4
    0.95
    TER
    0.94
     مختلف
    0.93
    Activations Density 0.000%

    No Known Activations