© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97866
    Prev
    Next
    INDEX
    Explanations

    valid inputs

    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_14_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
     والن
    0.54
    <unused1640>
    0.50
     Exam
    0.50
    ंकि
    0.50
    Repr
    0.49
    ists
    0.48
     नंद
    0.48
     Aham
    0.47
    리티
    0.47
    ertid
    0.47
    POSITIVE LOGITS
     ör
    0.52
    using
    0.50
    ޟ
    0.50
    u
    0.50
     uses
    0.49
    Py
    0.48
     disorders
    0.48
     disorientation
    0.48
     smuggling
    0.48
    ені
    0.48
    Activations Density 0.004%

    No Known Activations