© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203801
    Prev
    Next
    INDEX
    Explanations

    When followed by a conditional clause

    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_6_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
    (
    1.05
    м
    0.91
    ↵↵↵
    0.86
    ي
    0.86
    ７
    0.83
     때
    0.82
    لی
    0.81
     \
    0.79
    、《
    0.79
    \,\
    0.79
    POSITIVE LOGITS
    an
    1.21
    the
    1.14
    n
    1.09
    ing
    0.96
    ul
    0.92
     the
    0.91
    ان
    0.90
    aduras
    0.85
     acide
    0.85
     fotografi
    0.83
    Activations Density 0.006%

    No Known Activations