© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204635
    Prev
    Next
    INDEX
    Explanations

    ABAP programs, Developer, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    is
    1.81
    c
    1.49
    s
    1.46
    ق
    1.45
    ع
    1.40
    m
    1.37
    to
    1.33
    k
    1.27
    ج
    1.27
    দ
    1.25
    POSITIVE LOGITS
    ların
    1.05
    ुलम
    0.95
    Nb
    0.90
    ﻞ
    0.87
     Бүген
    0.86
     لیکن
    0.83
     бывшего
    0.83
    ână
    0.83
     Наи
    0.82
    losti
    0.81
    Activations Density 0.000%

    No Known Activations