© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10851
    Prev
    Next
    INDEX
    Explanations

    objective-c and swift imports

    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
    飼
    0.41
    私募基金
    0.39
     Transportation
    0.38
     microtubules
    0.38
    semer
    0.38
     Öffentlichkeit
    0.38
     Category
    0.38
    Wildlife
    0.37
     category
    0.36
     dbo
    0.36
    POSITIVE LOGITS
     雪
    0.42
    striction
    0.41
     imported
    0.39
    зне
    0.39
    教师
    0.37
    导入
    0.37
     बेरोजगारी
    0.37
     importing
    0.37
    été
    0.36
    KD
    0.36
    Activations Density 0.001%

    No Known Activations