© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261208
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    p
    1.77
    1
    1.70
    ב
    1.70
    ال
    1.51
    Ма
    1.36
    ര്‍
    1.34
    x
    1.33
    У
    1.32
    К
    1.31
    W
    1.30
    POSITIVE LOGITS
    ene
    1.00
    йки
    0.96
    ка
    0.95
     desempeñ
    0.94
    <0xBE>
    0.93
     incentiv
    0.87
     режисс
    0.87
    ాన
    0.86
     و
    0.86
     matem
    0.85
    Activations Density 0.000%

    No Known Activations