© 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. 130769
    Prev
    Next
    INDEX
    Explanations

    built by or founded by historical figures

    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
     durability
    0.41
     aback
    0.39
    apas
    0.38
    ता
    0.38
    atre
    0.38
    하
    0.37
    내
    0.37
    騫
    0.37
    ऊंगा
    0.36
     beetje
    0.36
    POSITIVE LOGITS
    ീസ്
    0.40
     Besançon
    0.39
     Gemeins
    0.38
    滙
    0.38
     связано
    0.38
    stanbul
    0.38
     京都
    0.37
     ලෙස
    0.37
    を活用
    0.37
     روس
    0.37
    Activations Density 0.004%

    No Known Activations