© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44271
    Prev
    Next
    INDEX
    Explanations

    if clauses

    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_22_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
     שם
    0.45
    this
    0.41
    ↵↵↵
    0.41
     Charles
    0.39
    è
    0.39
     Amazon
    0.38
     चार्ल्स
    0.38
     Alexandre
    0.38
    </blockquote>
    0.37
    Charles
    0.37
    POSITIVE LOGITS
     نحاول
    0.56
     мог
    0.50
     могли
    0.47
     یورپی
    0.46
     prib
    0.42
     podrían
    0.42
     podría
    0.41
    нили
    0.41
     сможете
    0.40
    ದುಕೊಳ್ಳ
    0.40
    Activations Density 0.025%

    No Known Activations