© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221173
    Prev
    Next
    INDEX
    Explanations

    handling and steering

    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_31_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
     drivetrain
    0.37
     التحكم
    0.36
    踱
    0.34
    forward
    0.33
     magnitude
    0.33
     گذشته
    0.33
     controlling
    0.33
     jazdy
    0.33
    行驶
    0.32
     불안
    0.32
    POSITIVE LOGITS
    暢
    0.38
    營業
    0.35
     публі
    0.34
     хірур
    0.33
     antibiotic
    0.32
     surgical
    0.31
    替え
    0.31
    antib
    0.31
    ্যানে
    0.31
     pediatric
    0.31
    Activations Density 0.002%

    No Known Activations