© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6441
    Prev
    Next
    INDEX
    Explanations

    describing actions/experiences

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    燔
    0.41
    ifo
    0.39
     Died
    0.38
    Lig
    0.38
     फाइव
    0.38
    ToList
    0.38
     उपा
    0.38
    ACS
    0.37
     Mond
    0.37
    اویر
    0.37
    POSITIVE LOGITS
     stepped
    0.46
    歩
    0.45
     sighed
    0.44
    stepping
    0.44
     stepping
    0.43
     berdiri
    0.42
    抬头
    0.42
    ood
    0.42
     walk
    0.41
    Walking
    0.41
    Activations Density 0.063%

    No Known Activations