© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4134
    Prev
    Next
    INDEX
    Explanations

    pronoun then action

    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_38_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
     freeze
    0.46
    沂
    0.45
     ilus
    0.40
    ेंज
    0.40
     freezes
    0.40
     ilusión
    0.38
     yed
    0.38
    🕎
    0.38
    ндай
    0.38
     goto
    0.37
    POSITIVE LOGITS
     leaving
    0.79
     reaching
    0.78
     abandoning
    0.78
     Leaving
    0.77
     taking
    0.76
     removing
    0.73
     Taking
    0.73
     ignoring
    0.73
    Leaving
    0.73
     putting
    0.70
    Activations Density 0.088%

    No Known Activations