© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41893
    Prev
    Next
    INDEX
    Explanations

    lane keeping assist and masking

    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
     secrecy
    0.38
    cić
    0.37
     fleet
    0.34
     prayers
    0.32
    Throws
    0.30
    配合
    0.29
    🇾
    0.29
     chambers
    0.29
     знали
    0.29
     tarses
    0.28
    POSITIVE LOGITS
    πο
    0.30
    Cumulative
    0.30
     توسط
    0.29
    Всім
    0.29
     જવાબ
    0.29
    ったら
    0.28
     minimale
    0.28
    Robinson
    0.28
    :+
    0.28
     ۳
    0.28
    Activations Density 0.002%

    No Known Activations