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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216765
    Prev
    Next
    INDEX
    Explanations

    hours

    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_47_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
    두
    0.40
    二
    0.38
    alahan
    0.37
     అ
    0.36
    這一
    0.36
     Zd
    0.36
    როს
    0.36
     डेंटल
    0.35
    쓴
    0.35
    iven
    0.34
    POSITIVE LOGITS
    せず
    0.40
    ট্রোল
    0.38
     Trabaj
    0.38
    ন্থ
    0.38
    ेंटीना
    0.37
     untouch
    0.37
    лік
    0.36
     uncontrolled
    0.35
    🕰
    0.35
    នៃការ
    0.35
    Activations Density 0.004%

    No Known Activations