© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166700
    Prev
    Next
    INDEX
    Explanations

    async

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     requ
    0.40
    ++;
    0.39
    .//
    0.38
     req
    0.38
    onal
    0.37
     as
    0.36
     demand
    0.35
    requis
    0.35
    ++.
    0.35
    )?.
    0.35
    POSITIVE LOGITS
    function
    0.56
     function
    0.54
     (_
    0.54
     fonction
    0.51
     ():
    0.50
     функция
    0.47
     funzione
    0.47
    unction
    0.47
     (__
    0.47
     función
    0.46
    Activations Density 0.000%

    No Known Activations