© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196257
    Prev
    Next
    INDEX
    Explanations

    function arguments and code structure

    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
     Underlying
    0.40
    禀
    0.37
    mapStateToProps
    0.36
     dispose
    0.36
    oreille
    0.36
    жени
    0.35
    formData
    0.35
    柅
    0.34
     एक्सप्लेन
    0.34
     domande
    0.34
    POSITIVE LOGITS
     psy
    0.40
     psychology
    0.38
     psyk
    0.38
     psih
    0.38
     few
    0.38
     paar
    0.38
    few
    0.37
    心理
    0.37
     Psychology
    0.37
     psicologia
    0.37
    Activations Density 0.000%

    No Known Activations