© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197426
    Prev
    Next
    INDEX
    Explanations

    gibberish punctuation sequences

    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_15_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
     ਆਪਣ
    0.57
     पाह
    0.53
    :@"
    0.51
    ruire
    0.49
     direitos
    0.49
     निहित
    0.49
     dışında
    0.49
    िया
    0.48
     그러나
    0.46
    と同様
    0.46
    POSITIVE LOGITS
    O
    0.55
     handcuffed
    0.52
    z
    0.51
    al
    0.51
    LE
    0.50
    s
    0.50
    ষ্টিত
    0.47
     wrinkled
    0.47
    elius
    0.47
     Lek
    0.46
    Activations Density 0.005%

    No Known Activations