© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67138
    Prev
    Next
    INDEX
    Explanations

    pro

    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_51_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
     ञ
    0.38
     Dario
    0.38
    contentInset
    0.37
     Darius
    0.35
     spo
    0.34
    guy
    0.34
     নক
    0.34
     নত
    0.34
    勋
    0.33
    Dad
    0.32
    POSITIVE LOGITS
    プロ
    2.08
     프로
    1.95
     PRO
    1.88
    PRO
    1.83
     प्रो
    1.78
     પ્રો
    1.77
    프로
    1.76
     プロ
    1.75
    про
    1.74
     Про
    1.63
    Activations Density 0.029%

    No Known Activations