© 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. 43068
    Prev
    Next
    INDEX
    Explanations

    Incheon International

    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
    ่ง
    0.70
    v
    0.69
     anos
    0.68
    ین
    0.65
    자는
    0.64
    ונה
    0.64
    لی
    0.63
    บุคคล
    0.63
    K
    0.63
     aye
    0.61
    POSITIVE LOGITS
    +
    0.79
    ٠
    0.69
     by
    0.66
    _
    0.65
     verbinden
    0.64
    ?
    0.62
    #:
    0.62
     transporte
    0.59
    ၻ
    0.59
    0
    0.57
    Activations Density 0.000%

    No Known Activations