© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124598
    Prev
    Next
    INDEX
    Explanations

    introduces content or features

    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_3_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
    م
    0.76
    ك
    0.76
    ک
    0.74
     in
    0.71
    fortunately
    0.70
    ד
    0.70
    ના
    0.68
    ä
    0.64
    ずつ
    0.64
    بك
    0.64
    POSITIVE LOGITS
    0.78
    I
    0.63
    т
    0.59
     pasa
    0.55
     fillColor
    0.52
    ევრი
    0.52
    /
    0.52
    IA
    0.50
    actor
    0.50
     favicon
    0.50
    Activations Density 0.004%

    No Known Activations