© 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. 60649
    Prev
    Next
    INDEX
    Explanations

    opening punctuation

    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
    არის
    0.67
    ის
    0.63
    étaient
    0.60
    ن
    0.59
    листы
    0.59
    න්
    0.59
    ول
    0.57
     वाजिब
    0.56
    اعات
    0.56
    την
    0.55
    POSITIVE LOGITS
    ↵
    0.72
    v
    0.64
    d
    0.60
    ha
    0.59
    cr
    0.59
    ทั้ง
    0.58
    ý
    0.56
     ancak
    0.54
    p
    0.54
    her
    0.53
    Activations Density 0.093%

    No Known Activations