© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1488
    Prev
    Next
    INDEX
    Explanations

    DEFAULT CURRENT_TIMESTAMP or NULL

    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_39_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
    oughby
    0.37
    尣
    0.36
     उदासीन
    0.35
     homologous
    0.35
     Гри
    0.35
     höher
    0.35
     unimaginable
    0.35
    κτήθηκε
    0.34
    اویز
    0.34
     Kenyon
    0.34
    POSITIVE LOGITS
     tr
    0.38
    <start_of_image>
    0.37
    iti
    0.37
     prim
    0.34
     searching
    0.34
     die
    0.33
     arm
    0.33
    overview
    0.32
    Ang
    0.32
    tool
    0.32
    Activations Density 0.003%

    No Known Activations