© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81490
    Prev
    Next
    INDEX
    Explanations

    lazy

    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_0_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
    ją
    1.36
    ین
    1.35
    য়
    1.32
    тальян
    1.31
    наче
    1.24
    zī
    1.24
    yı
    1.23
    ו
    1.21
    т
    1.19
    л
    1.19
    POSITIVE LOGITS
    8
    1.96
    0
    1.91
    。
    1.91
    大
    1.91
    2
    1.88
    9
    1.78
    أ
    1.75
    ing
    1.73
    7
    1.70
    3
    1.68
    Activations Density 0.001%

    No Known Activations