© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122600
    Prev
    Next
    INDEX
    Explanations

    detects 'if' statements

    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_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     therapists
    0.44
     flexible
    0.40
    체
    0.39
     waves
    0.39
     therapist
    0.39
     ethnicity
    0.38
    flexible
    0.37
     성공
    0.37
     therapy
    0.37
    ôn
    0.37
    POSITIVE LOGITS
    Activation
    0.43
     звез
    0.39
    Invalid
    0.39
    IVATE
    0.38
    CreateInfo
    0.38
    .|__
    0.37
    监听页面
    0.36
    ("*
    0.36
    ʣ
    0.35
     அலுவ
    0.34
    Activations Density 0.000%

    No Known Activations