© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48410
    Prev
    Next
    INDEX
    Explanations

    closing code delimiters like `};` and `})`orend of code blocks and JSON structure

    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_10_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
    冎
    0.65
    م
    0.60
    鋃
    0.59
     త
    0.59
    泺
    0.57
    ar
    0.55
     البطولة
    0.54
    м
    0.54
     و
    0.54
     be
    0.53
    POSITIVE LOGITS
    на
    0.72
    ED
    0.71
    O
    0.71
    า
    0.65
    ES
    0.64
     consente
    0.63
    6
    0.61
    י
    0.61
    де
    0.59
    ะ
    0.59
    Activations Density 0.024%

    No Known Activations