© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159781
    Prev
    Next
    INDEX
    Explanations

    ambiguity

    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_2_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
    ת
    1.71
    ة
    1.64
    ן
    1.63
    ي
    1.44
    ק
    1.44
    ية
    1.35
    י
    1.32
    ە
    1.29
    ۔
    1.26
    ೆ
    1.20
    POSITIVE LOGITS
     for
    1.50
    ER
    1.30
    for
    1.23
    ?
    1.17
     of
    1.16
    (
    1.16
    {{
    1.16
    ور
    1.15
    RE
    1.10
    the
    1.07
    Activations Density 0.002%

    No Known Activations