© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    programming context

    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
    ItemLayout
    0.40
    CLES
    0.40
    ramiento
    0.38
    setAttribute
    0.38
    armos
    0.37
    蟠
    0.37
    opathy
    0.37
    बिनेट
    0.37
    লাষ
    0.36
    linejoin
    0.36
    POSITIVE LOGITS
     MOBILE
    0.41
     mobile
    0.41
    Mobile
    0.41
     Mobile
    0.40
    ادله
    0.39
     lá
    0.36
     crater
    0.36
     NCP
    0.36
    MOBILE
    0.36
    꾀
    0.35
    Activations Density 0.022%

    No Known Activations