© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38320
    Prev
    Next
    INDEX
    Explanations

    boilerplate

    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_11_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
    Ni
    0.47
     इसकी
    0.46
    क्षी
    0.46
    L
    0.45
    Ds
    0.45
     त्यांच्या
    0.45
     इस्तेमाल
    0.45
     avenues
    0.45
    s
    0.45
     toughness
    0.44
    POSITIVE LOGITS
    к
    0.52
     historische
    0.52
     Prison
    0.51
     Playboy
    0.49
    تالي
    0.48
    ку
    0.47
     Shakespeare
    0.47
    తా
    0.47
    oriale
    0.46
     கட்சிய
    0.45
    Activations Density 0.001%

    No Known Activations