© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78593
    Prev
    Next
    INDEX
    Explanations

    phrases indicating language or 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_31_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
     bullion
    0.41
     buttery
    0.38
    或者是
    0.38
     rarest
    0.38
    熟悉的
    0.37
    तील
    0.37
     ឬ
    0.36
     বলিব
    0.36
    经典的
    0.36
     pétales
    0.36
    POSITIVE LOGITS
    inking
    0.36
    oming
    0.36
     EXPRESS
    0.35
    aggo
    0.35
     எங்க
    0.35
    آمد
    0.34
    洿
    0.34
     উচিত
    0.34
     especially
    0.33
     therefore
    0.33
    Activations Density 0.030%

    No Known Activations