© 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. 35195
    Prev
    Next
    INDEX
    Explanations

    monsoon, mononobe, mongodb

    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
    k
    0.89
    y
    0.78
    ly
    0.76
     externe
    0.71
    j
    0.66
     Voraus
    0.64
     Ꭰ
    0.64
    r
    0.63
     verwend
    0.59
    ו
    0.59
    POSITIVE LOGITS
    0
    0.78
    ت
    0.73
    غ
    0.70
    ان
    0.64
    esan
    0.63
     یا
    0.63
    보
    0.62
    祺
    0.62
    ᐉ
    0.61
    انس
    0.61
    Activations Density 0.009%

    No Known Activations