© 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. 248958
    Prev
    Next
    INDEX
    Explanations

    like / as translation

    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
     thành
    0.44
    成
    0.43
     الصغيرة
    0.42
    諒
    0.41
    Ŕ
    0.39
     حصے
    0.38
    ಟ್ರ
    0.38
    SplitContainer
    0.38
    ተ
    0.38
    యన
    0.38
    POSITIVE LOGITS
     όπως
    0.48
     seperti
    0.47
    जैसे
    0.47
    如
    0.47
     जैसे
    0.46
     مانند
    0.45
     își
    0.45
     как
    0.43
     comme
    0.42
     zoals
    0.42
    Activations Density 0.000%

    No Known Activations