© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130203
    Prev
    Next
    INDEX
    Explanations

    Tokyo Metropolitan Government Building

    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_25_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
    But
    0.37
    ahanam
    0.35
    “
    0.35
    ‘
    0.35
     “
    0.34
     ya
    0.34
     Siamese
    0.33
     But
    0.33
    淘汰
    0.32
    組み
    0.32
    POSITIVE LOGITS
    𝗻
    0.37
    ிரஸ்
    0.37
     média
    0.37
     лигасы
    0.37
     यूएस
    0.37
    öffnung
    0.37
     Regan
    0.35
    edition
    0.35
     относится
    0.35
    ToJson
    0.34
    Activations Density 0.000%

    No Known Activations