© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89815
    Prev
    Next
    INDEX
    Explanations

    anti-matter, AntiGPT mode

    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_3_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
     It
    0.87
    у
    0.82
    ка
    0.78
    ens
    0.76
    с
    0.74
    یس
    0.72
    ф
    0.71
    It
    0.70
    یت
    0.70
    ots
    0.69
    POSITIVE LOGITS
    n
    0.77
    l
    0.67
    al
    0.60
    。
    0.60
     اړه
    0.59
    cón
    0.58
     ניתן
    0.57
    r
    0.57
    ಿಗ
    0.56
     zoveel
    0.56
    Activations Density 0.001%

    No Known Activations