© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178708
    Prev
    Next
    INDEX
    Explanations

    Ou

    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_50_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
    ైనా
    0.44
    юнча
    0.43
    Tina
    0.39
     घेतला
    0.39
    呷
    0.39
     ख़
    0.39
    rawn
    0.38
    ಾಲ
    0.38
    lina
    0.37
     Lina
    0.37
    POSITIVE LOGITS
    irio
    0.47
    Bry
    0.41
    怒
    0.39
     Angry
    0.38
    atte
    0.37
     Blade
    0.36
     angry
    0.35
    odium
    0.35
     loudly
    0.35
     நடத்து
    0.35
    Activations Density 0.000%

    No Known Activations