© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234803
    Prev
    Next
    INDEX
    Explanations

    say theories

    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
    শ্চ
    0.39
    젬
    0.37
     Cont
    0.37
    ಿಕೊಂಡು
    0.37
    ल्ल्या
    0.36
    راعظم
    0.35
     적극
    0.35
     шка
    0.34
     boa
    0.34
    軫
    0.33
    POSITIVE LOGITS
     theories
    2.33
     theory
    2.31
     Theory
    2.09
     teor
    2.09
    Theory
    2.08
     Theories
    2.06
     teorías
    2.06
     teori
    2.05
    theory
    2.03
     теории
    2.03
    Activations Density 0.002%

    No Known Activations