© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31864
    Prev
    Next
    INDEX
    Explanations

    its core

    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
     surpr
    0.44
    ।--
    0.41
    Components
    0.41
    ("--
    0.41
    iativa
    0.40
    راضي
    0.39
     Components
    0.38
     components
    0.38
    urence
    0.37
    솜
    0.36
    POSITIVE LOGITS
    nature
    0.44
     людей
    0.41
    鸡蛋
    0.41
     nature
    0.40
     laid
    0.39
     जन्म
    0.39
    မြင့်
    0.39
     rộng
    0.37
    క్ష
    0.37
     Fundamental
    0.37
    Activations Density 0.007%

    No Known Activations