© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216452
    Prev
    Next
    INDEX
    Explanations

    specific names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     Telf
    0.44
     CP
    0.39
    CP
    0.38
     Artik
    0.38
    ugeot
    0.37
     отличие
    0.37
     Tel
    0.37
     R
    0.36
     Charles
    0.36
     CPE
    0.36
    POSITIVE LOGITS
    ᱶ
    0.41
     obes
    0.40
    ষধ
    0.39
     recense
    0.37
    格局
    0.37
     Never
    0.37
     Moral
    0.36
     infer
    0.36
    AVE
    0.36
    Marker
    0.35
    Activations Density 0.011%

    No Known Activations