© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196243
    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_26_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
    A
    0.48
    Where
    0.43
    The
    0.43
     for
    0.42
    Access
    0.42
    Expect
    0.41
    by
    0.41
    /*
    0.41
    in
    0.41
    col
    0.40
    POSITIVE LOGITS
     Hôm
    0.52
     bénéf
    0.51
     सूचीबद्ध
    0.50
    waterslide
    0.50
    やすい
    0.49
     deuxième
    0.49
    ೫
    0.49
     인기
    0.49
    メリット
    0.48
     आश्चर्य
    0.48
    Activations Density 0.000%

    No Known Activations