© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199172
    Prev
    Next
    INDEX
    Explanations

    screen size

    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_27_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
     [&
    0.36
     reflexes
    0.36
     responded
    0.36
     lengthened
    0.34
     preju
    0.33
    قتصاد
    0.32
     announced
    0.32
     responds
    0.32
    Funds
    0.31
     estimated
    0.31
    POSITIVE LOGITS
     За
    0.38
    äck
    0.37
     માં
    0.37
     Де
    0.36
    闱
    0.36
    yrıca
    0.35
    יית
    0.35
     Таким
    0.35
     त्रुट
    0.34
     Запа
    0.34
    Activations Density 0.000%

    No Known Activations