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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30593
    Prev
    Next
    INDEX
    Explanations

    react hooks

    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_40_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
    唯
    0.41
     नित
    0.39
    Bowling
    0.38
    Fit
    0.37
    UKI
    0.36
    kten
    0.36
    FRAM
    0.36
    ("/{
    0.36
    stressed
    0.36
     Bowling
    0.35
    POSITIVE LOGITS
     imperative
    0.55
     necessity
    0.51
    imper
    0.49
     необходимости
    0.49
     Imper
    0.43
    Imper
    0.43
    Necess
    0.42
     imperatives
    0.41
     imper
    0.41
    必要
    0.41
    Activations Density 0.000%

    No Known Activations