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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207643
    Prev
    Next
    INDEX
    Explanations

    leaf or Chinese characters for leaf

    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_20_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
    …?
    0.47
    ’:
    0.46
    ？」
    0.45
     ASCII
    0.45
     Unicode
    0.45
    tourism
    0.44
    igators
    0.43
    CHREIB
    0.43
    ：「
    0.42
     apolog
    0.42
    POSITIVE LOGITS
     ainult
    0.46
    ">)</
    0.42
     alleen
    0.42
    Цена
    0.42
     всіх
    0.42
     μόνο
    0.41
    伈
    0.40
    ना
    0.40
     niemals
    0.39
    Olivia
    0.39
    Activations Density 0.000%

    No Known Activations