© 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. 130509
    Prev
    Next
    INDEX
    Explanations

    input followed by colon

    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
     educational
    0.39
     functional
    0.37
    }^{\
    0.37
    ភាគ
    0.36
     generative
    0.36
     acet
    0.35
     tart
    0.35
     preprocess
    0.35
     pât
    0.35
     বিভ
    0.35
    POSITIVE LOGITS
    യും
    0.40
     drains
    0.39
    圳
    0.39
    それぞれ
    0.38
    và
    0.38
    宝
    0.38
    有没有
    0.37
     accepté
    0.37
     عجیب
    0.37
    उनकी
    0.36
    Activations Density 0.004%

    No Known Activations