© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212064
    Prev
    Next
    INDEX
    Explanations

    Chinese and English mixed texts

    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_19_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
     সরে
    0.43
    pt
    0.42
    aport
    0.40
     {//
    0.40
     trasform
    0.40
     Assemblies
    0.40
    Parliament
    0.39
    }-{
    0.39
    뿔
    0.38
    નારા
    0.38
    POSITIVE LOGITS
     flashing
    0.50
    मिका
    0.50
     trapped
    0.48
    вища
    0.48
     besch
    0.46
    віч
    0.45
     совер
    0.45
     ничек
    0.45
    接收
    0.45
     velas
    0.45
    Activations Density 0.000%

    No Known Activations