© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246332
    Prev
    Next
    INDEX
    Explanations

    lane keeping assist

    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_40_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
    ikor
    0.44
    speakers
    0.40
    stacks
    0.40
    mates
    0.39
    객
    0.39
    GRAM
    0.38
    Borrowed
    0.38
    加
    0.38
     uncomfortable
    0.38
     AGA
    0.37
    POSITIVE LOGITS
     initState
    0.41
     Bacteriol
    0.38
     Solution
    0.37
     solution
    0.36
     विभाजन
    0.36
    clides
    0.36
    cInfo
    0.36
     Онлайн
    0.35
    лиз
    0.35
     marking
    0.35
    Activations Density 0.000%

    No Known Activations