© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50179
    Prev
    Next
    INDEX
    Explanations

    data

    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_55_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
    .°
    0.40
    数组
    0.39
    Istituto
    0.39
     array
    0.38
     },{
    0.37
     массива
    0.36
     :{
    0.36
    Ộ
    0.35
    Array
    0.35
    规划
    0.35
    POSITIVE LOGITS
    [,
    0.55
     <-
    0.52
    <-
    0.43
     있다
    0.40
    //
    0.37
     Milling
    0.37
    datasets
    0.37
     treated
    0.37
    [/
    0.37
     ing
    0.36
    Activations Density 0.001%

    No Known Activations