© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59503
    Prev
    Next
    INDEX
    Explanations

    droppin' or droppings

    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_2_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
     اینکه
    0.93
     ότι
    0.90
     εξ
    0.90
     می‌کند
    0.83
    ۰
    0.83
    値
    0.82
     εν
    0.82
    の特徴
    0.81
     می‌دهد
    0.81
    高い
    0.81
    POSITIVE LOGITS
    h
    1.77
    y
    1.77
    at
    1.67
    ed
    1.56
    t
    1.52
    i
    1.41
    ي
    1.38
    v
    1.30
    ا
    1.30
    d
    1.22
    Activations Density 0.002%

    No Known Activations