© 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. 2578
    Prev
    Next
    INDEX
    Explanations

    Kenya, grilled meat, Acts of Parliament

    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
    reter
    0.43
     qualcosa
    0.40
    zess
    0.37
    jati
    0.36
     Vide
    0.36
     pho
    0.36
    灑
    0.36
     Reis
    0.36
    创造
    0.36
     viaggi
    0.36
    POSITIVE LOGITS
    érie
    0.39
     Kenya
    0.37
     '**
    0.37
    Kenya
    0.37
     Wadd
    0.36
    ᵈ
    0.36
    raf
    0.35
    워크
    0.35
    ̾
    0.34
     Entity
    0.34
    Activations Density 0.011%

    No Known Activations