© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167722
    Prev
    Next
    INDEX
    Explanations

    http

    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
     blast
    0.41
     }}">
    0.40
    খী
    0.37
     glove
    0.37
     ليست
    0.37
    বিস্ত
    0.37
     unst
    0.36
     coher
    0.36
     రచన
    0.36
     মুহুর
    0.36
    POSITIVE LOGITS
     Page
    0.50
    Page
    0.48
    toByteArray
    0.45
    頁
    0.44
     página
    0.44
     page
    0.42
     halaman
    0.41
     الصفحة
    0.41
    ]$
    0.41
     페이지
    0.41
    Activations Density 0.000%

    No Known Activations