© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10982
    Prev
    Next
    INDEX
    Explanations

    Denmark or Danish

    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_13_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
    amber
    0.33
    c
    0.33
    k
    0.31
     (
    0.31
     encoded
    0.31
    ane
    0.30
    KT
    0.30
    ID
    0.30
     invers
    0.29
     encode
    0.29
    POSITIVE LOGITS
    ൦
    0.40
     Messina
    0.39
    🉐
    0.38
     FGD
    0.37
    
    0.35
     AGC
    0.35
     Ах
    0.35
    ським
    0.35
    సిన
    0.34
    зион
    0.34
    Activations Density 0.007%

    No Known Activations