© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125113
    Prev
    Next
    INDEX
    Explanations

    sit or sat followed by location/posture

    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
     Challenge
    0.40
    enaar
    0.38
     Moreton
    0.37
    ન્ન
    0.37
     challenge
    0.36
    ༨
    0.36
    ntag
    0.35
    、​
    0.34
     CHALL
    0.34
    留
    0.34
    POSITIVE LOGITS
     skewed
    0.45
    Skew
    0.42
     skew
    0.37
    Crypt
    0.36
    Silent
    0.36
    crypt
    0.35
     Satt
    0.35
     recep
    0.34
    엷
    0.34
    িয়৷
    0.34
    Activations Density 0.002%

    No Known Activations