© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 64138
    Prev
    Next
    INDEX
    Explanations

    imported as a module

    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_41_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
     python
    0.47
    Python
    0.46
     Python
    0.46
    python
    0.46
     PYTHON
    0.43
    類
    0.39
    PYTHON
    0.38
    ython
    0.38
    蟒
    0.38
    ジャパン
    0.37
    POSITIVE LOGITS
     dentro
    0.50
     binnen
    0.48
     within
    0.47
     fromi
    0.47
     from
    0.47
     everywhere
    0.47
    听
    0.44
     داخل
    0.43
    从
    0.40
     innerhalb
    0.40
    Activations Density 0.001%

    No Known Activations