© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44640
    Prev
    Next
    INDEX
    Explanations

    arrest rates

    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
    기는
    0.52
    Detal
    0.47
    īgi
    0.45
    ↵↵↵↵↵↵↵↵
    0.45
     откуда
    0.45
    ↵↵↵↵↵↵↵
    0.44
    を作り
    0.44
    ımda
    0.43
    氙
    0.42
     [--
    0.42
    POSITIVE LOGITS
    selling
    0.51
    “
    0.47
     selling
    0.46
    роме
    0.45
    hill
    0.44
    с
    0.41
     predicting
    0.41
     capitalization
    0.40
     administering
    0.40
     benessere
    0.39
    Activations Density 0.001%

    No Known Activations