© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200321
    Prev
    Next
    INDEX
    Explanations

    special

    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
     মাথা
    0.34
    也好
    0.33
    改进
    0.33
    тини
    0.33
    勬
    0.33
     LEAD
    0.32
    맏
    0.32
    ্লীল
    0.32
    閒
    0.32
    companion
    0.32
    POSITIVE LOGITS
    Special
    0.65
     Special
    0.58
     special
    0.54
    pecial
    0.54
    特殊的
    0.52
     специальные
    0.51
     especial
    0.50
     особы
    0.50
     SPECIAL
    0.50
     специальных
    0.48
    Activations Density 0.000%

    No Known Activations