© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139602
    Prev
    Next
    INDEX
    Explanations

    temporal sequence indicators

    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_37_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
    قدم
    0.41
     قدم
    0.39
     نقدم
    0.38
    idam
    0.37
    ấ
    0.36
     contended
    0.36
     कायम
    0.36
    (^
    0.36
    шого
    0.35
    جمة
    0.34
    POSITIVE LOGITS
     last
    0.70
     next
    0.68
     prochaine
    0.64
     prochain
    0.59
     prossima
    0.58
     Next
    0.56
     prossimo
    0.56
     prochains
    0.56
    last
    0.54
     NEXT
    0.54
    Activations Density 0.005%

    No Known Activations