© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58954
    Prev
    Next
    INDEX
    Explanations

    Air support and Apple products

    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_11_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
    দের
    0.49
     samot
    0.41
     deterministic
    0.40
     systolic
    0.40
    ð
    0.40
    簸
    0.40
     smoothing
    0.39
    交通事故
    0.38
    자
    0.38
    ž
    0.37
    POSITIVE LOGITS
    ТА
    0.53
     Convent
    0.48
     Chanel
    0.48
     Bureau
    0.46
     Attack
    0.46
    attaque
    0.46
    shakespeare
    0.46
    documents
    0.46
     ataques
    0.46
    ithub
    0.46
    Activations Density 0.050%

    No Known Activations