© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42838
    Prev
    Next
    INDEX
    Explanations

    operating costs

    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_13_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
     ઊ
    0.59
     સ્ટ
    0.57
     SCHEDULE
    0.55
     douze
    0.55
     SBT
    0.55
     Gradle
    0.55
     ಮಾತನಾಡ
    0.55
     الطفل
    0.54
     S
    0.54
    Cul
    0.54
    POSITIVE LOGITS
    ier
    0.50
     operating
    0.48
    ジャー
    0.47
     operation
    0.45
    সমান
    0.44
     slips
    0.44
    𝗋
    0.43
    otomy
    0.43
    operating
    0.43
    optimized
    0.43
    Activations Density 0.039%

    No Known Activations