© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234115
    Prev
    Next
    INDEX
    Explanations

    wizard

    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_46_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
    Jesse
    0.42
    욘
    0.40
    蘋
    0.38
    Biden
    0.38
    скае
    0.37
     sawtooth
    0.37
    抡
    0.37
    膽
    0.36
    ńskim
    0.36
     मिरची
    0.36
    POSITIVE LOGITS
     wizard
    2.97
     Wizard
    2.84
     wizards
    2.80
    Wizard
    2.69
    wizard
    2.64
     Wizards
    2.50
     Wiz
    1.60
    wiz
    1.50
     magician
    1.46
     magicians
    1.46
    Activations Density 0.001%

    No Known Activations