© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24472
    Prev
    Next
    INDEX
    Explanations

    Country

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    grip
    0.42
    Aluminum
    0.37
     aluminum
    0.36
     tuck
    0.35
     obie
    0.35
    ^{\#}\
    0.34
     Aluminum
    0.34
    캔
    0.34
     تجویز
    0.33
     grip
    0.33
    POSITIVE LOGITS
     Country
    2.17
    Country
    2.09
     COUNTRY
    2.03
     country
    2.02
    COUNTRY
    1.94
    country
    1.84
     país
    1.76
     Countries
    1.71
     страны
    1.71
     देश
    1.70
    Activations Density 0.017%

    No Known Activations