© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13942
    Prev
    Next
    INDEX
    Explanations

    numbers and country names

    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
    ابية
    0.37
     Lords
    0.35
    '}
    0.35
     ação
    0.34
     trove
    0.34
     Nee
    0.34
    降
    0.34
    },"
    0.33
     入
    0.33
     রেফার
    0.33
    POSITIVE LOGITS
    varphi
    0.44
     phe
    0.38
     nurture
    0.38
    innerWidth
    0.37
    seab
    0.37
     yal
    0.37
    prestations
    0.37
    சிவ
    0.36
    Matthew
    0.36
    ostal
    0.36
    Activations Density 0.008%

    No Known Activations