© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164753
    Prev
    Next
    INDEX
    Explanations

    `fmt.Printf`

    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_13_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
    og
    0.63
    р
    0.57
    د
    0.57
    snapshot
    0.54
    Graph
    0.53
    রা
    0.51
    Ni
    0.50
    ঃ
    0.50
    ্রে
    0.50
    Name
    0.49
    POSITIVE LOGITS
    atsioon
    0.50
    !...
    0.49
     χρόνια
    0.48
    一年
    0.48
    イング
    0.47
     headphones
    0.47
     അവർ
    0.46
     Unidos
    0.46
    联盟
    0.46
    ...'
    0.46
    Activations Density 0.002%

    No Known Activations