© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46758
    Prev
    Next
    INDEX
    Explanations

    portuguese language

    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_3_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
    I
    0.80
    hane
    0.68
    ource
    0.59
     I
    0.58
    OUSE
    0.58
    NoSuch
    0.58
    澫
    0.58
    ጠት
    0.57
    enced
    0.57
    udo
    0.57
    POSITIVE LOGITS
    га
    0.78
    ৩
    0.75
    ја
    0.70
    امة
    0.68
    يد
    0.66
    ма
    0.65
    𝒊
    0.65
     سي
    0.64
    يان
    0.64
    та
    0.63
    Activations Density 0.000%

    No Known Activations