© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126902
    Prev
    Next
    INDEX
    Explanations

    river delta, Thai, Euro

    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
    را
    0.64
    ە
    0.61
    ری
    0.61
    alg
    0.61
    İN
    0.61
    ین
    0.60
    ير
    0.59
    ▔
    0.58
    خ
    0.56
    تس
    0.55
    POSITIVE LOGITS
    us
    0.84
    is
    0.75
    ى
    0.75
    quiera
    0.70
     sluggish
    0.66
    efeller
    0.65
    y
    0.64
    이었다
    0.61
    ated
    0.61
    ต์
    0.60
    Activations Density 0.000%

    No Known Activations