© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15413
    Prev
    Next
    INDEX
    Explanations

    planning, drilling, pulling

    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_15_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
    models
    0.36
    cones
    0.35
    log
    0.35
    onclick
    0.35
    ゼ
    0.32
    get
    0.32
    投資
    0.32
    āj
    0.32
    clock
    0.32
    System
    0.31
    POSITIVE LOGITS
     мы
    0.42
    }]$.
    0.40
     kayna
    0.39
     обычно
    0.38
     cultivator
    0.38
     करना
    0.37
     ні
    0.37
     находится
    0.37
     n
    0.36
    يًا
    0.36
    Activations Density 0.041%

    No Known Activations