© 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. 116045
    Prev
    Next
    INDEX
    Explanations

    UC Berkeley

    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
    游
    0.42
    Net
    0.40
    <0xC2>
    0.37
     We
    0.37
    loader
    0.36
    S
    0.36
    battle
    0.36
    Cm
    0.35
    <0x0D>
    0.35
    dX
    0.35
    POSITIVE LOGITS
     investigação
    0.43
     investigación
    0.42
    ពិស
    0.40
     института
    0.40
     testclass
    0.39
     psicología
    0.38
     психо
    0.38
     তদন্ত
    0.38
     제작
    0.38
    UseDebug
    0.38
    Activations Density 0.003%

    No Known Activations