© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2533
    Prev
    Next
    INDEX
    Explanations

    doing or will do actions

    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_39_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
    ivate
    0.40
    窮
    0.40
     adherent
    0.39
    गाई
    0.38
    PageState
    0.38
    iewa
    0.37
    plic
    0.36
    楊
    0.36
    ocally
    0.36
    ingen
    0.36
    POSITIVE LOGITS
     करने
    1.00
     করার
    0.97
     करना
    0.95
     করে
    0.95
     doing
    0.93
     Doing
    0.93
     ചെയ്യ
    0.92
     کرنے
    0.90
     করা
    0.90
    做
    0.90
    Activations Density 0.014%

    No Known Activations