© 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. 253129
    Prev
    Next
    INDEX
    Explanations

    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
     thuần
    0.38
     hom
    0.38
     เพื่อ
    0.37
     ដើម្បី
    0.37
     compatible
    0.37
     üzerinde
    0.36
    -'
    0.36
     '':
    0.35
     homologous
    0.35
     folos
    0.35
    POSITIVE LOGITS
     слова
    0.49
     كلمات
    0.48
     بالح
    0.46
     WORDS
    0.46
     слов
    0.46
    눈
    0.45
     words
    0.45
    words
    0.44
     Words
    0.44
     눈
    0.43
    Activations Density 0.000%

    No Known Activations