© 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. 131254
    Prev
    Next
    INDEX
    Explanations

    multi-language text

    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
     PJ
    0.47
     HJ
    0.41
     çi
    0.40
     Tài
    0.39
    ープ
    0.39
     EJ
    0.38
     PN
    0.38
    ဳ
    0.38
     तै
    0.37
    輝
    0.36
    POSITIVE LOGITS
     들
    0.98
    들
    0.49
    들이
    0.42
    DLL
    0.41
    Bas
    0.41
    入れ
    0.41
    󠁥
    0.40
    烫
    0.40
    dele
    0.39
    basin
    0.39
    Activations Density 0.000%

    No Known Activations