© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27428
    Prev
    Next
    INDEX
    Explanations

    not found or be able

    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_10_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
    ك
    0.55
    ق
    0.52
    ع
    0.51
    ה
    0.48
    وك
    0.44
    ві
    0.41
    8
    0.41
    official
    0.41
    வ
    0.41
    ј
    0.41
    POSITIVE LOGITS
    ropolitan
    0.38
     եւ
    0.38
    स्तक
    0.36
     aching
    0.35
     ABSORBED
    0.35
    riz
    0.35
    lir
    0.35
    j
    0.35
     tiết
    0.34
    ators
    0.34
    Activations Density 0.122%

    No Known Activations