© 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. 2923
    Prev
    Next
    INDEX
    Explanations

    layers, depth measurements, and geological features

    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
     Nxf
    0.39
    妘
    0.39
    थुरा
    0.38
    Nie
    0.37
    ឆ្នាំ
    0.37
    popper
    0.36
     entityManager
    0.36
     दर्श
    0.36
    膦
    0.36
    ിക്കാം
    0.35
    POSITIVE LOGITS
     valley
    0.39
    ajana
    0.38
    increases
    0.38
     طب
    0.37
     Speedy
    0.37
    omio
    0.37
    ânea
    0.37
    load
    0.36
    oa
    0.36
     uveden
    0.36
    Activations Density 0.020%

    No Known Activations