© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24006
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    したもの
    0.72
    するもの
    0.70
     ایست
    0.69
    もの
    0.64
     것
    0.57
    อะไร
    0.40
    な
    0.39
    .​
    0.38
    lblCredits
    0.38
     もの
    0.38
    POSITIVE LOGITS
    andır
    0.87
    makt
    0.80
     dir
    0.78
    ものです
    0.78
    indir
    0.78
    ektir
    0.78
    ことです
    0.73
    ildir
    0.73
    dir
    0.72
    Dir
    0.70
    Activations Density 0.001%

    No Known Activations