© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52525
    Prev
    Next
    INDEX
    Explanations

    URLs with appended path separators

    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_31_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
    Para
    0.38
    Maar
    0.36
    Pour
    0.36
    ौरा
    0.36
    melting
    0.36
     Rolf
    0.36
    郯
    0.36
    㴓
    0.35
     рассчиты
    0.35
     ഫോ
    0.35
    POSITIVE LOGITS
     gallons
    0.40
     divinity
    0.39
     CY
    0.39
     completed
    0.37
     legacy
    0.37
     Divinity
    0.37
     am
    0.37
     perception
    0.35
     advocate
    0.35
     sample
    0.34
    Activations Density 0.002%

    No Known Activations