© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36776
    Prev
    Next
    INDEX
    Explanations

    inertial measurement, thermal imaging, inert gas

    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_11_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
    et
    0.42
    ्वेस्ट
    0.41
     certains
    0.41
    c
    0.41
    ations
    0.41
     December
    0.41
     Section
    0.40
     السادس
    0.40
    骧
    0.40
    inguishing
    0.40
    POSITIVE LOGITS
    リ
    0.48
     transluc
    0.45
    焔
    0.44
    箔
    0.44
    film
    0.43
    𝙾
    0.43
    ینو
    0.42
     透明
    0.42
     atmosfé
    0.42
    ಓ
    0.42
    Activations Density 0.061%

    No Known Activations