© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10883
    Prev
    Next
    INDEX
    Explanations

    Wales and Celtic regions

    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_40_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
    ubine
    0.37
    नीचर
    0.33
     Φ
    0.33
    Ordered
    0.33
     веке
    0.33
    在意
    0.32
     Istituto
    0.32
    扼
    0.32
     decided
    0.32
     रि
    0.32
    POSITIVE LOGITS
     Welsh
    0.72
     Wales
    0.64
     Celtic
    0.64
     celtic
    0.59
    Celtic
    0.58
    Wales
    0.58
     wales
    0.55
     Snowdon
    0.50
     Cornwall
    0.49
     Celt
    0.49
    Activations Density 0.046%

    No Known Activations