© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28762
    Prev
    Next
    INDEX
    Explanations

    post office

    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_10_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
    ۳
    0.85
     gradioApp
    0.79
    콴
    0.78
     пар
    0.76
     kelamin
    0.75
     kttt
    0.74
     NPTypeCode
    0.73
    ࿔
    0.73
     ϒ
    0.72
    σης
    0.71
    POSITIVE LOGITS
    r
    1.02
    ש
    0.92
     was
    0.91
    ر
    0.89
    اب
    0.88
    ق
    0.87
    ع
    0.86
     from
    0.85
    ال
    0.83
     of
    0.82
    Activations Density 0.001%

    No Known Activations