© 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. 261252
    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
    ية
    1.40
    َ
    1.13
    ุ
    1.09
    ן
    1.09
    ческой
    1.06
    یی
    1.02
    то
    1.00
    6
    0.99
    다
    0.97
    и
    0.95
    POSITIVE LOGITS
    a
    1.80
    ex
    1.37
    ה
    1.34
    ain
    1.33
    ik
    1.23
    한
    1.20
    ਾ
    1.20
    大
    1.18
    ana
    1.17
    v
    1.16
    Activations Density 0.000%

    No Known Activations