© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176255
    Prev
    Next
    INDEX
    Explanations

    yoga poses

    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_50_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
     Ak
    0.61
     ак
    0.58
     аку
    0.56
     ak
    0.55
     AK
    0.53
     আক
    0.53
    <0x92>
    0.52
    Ak
    0.49
     Ac
    0.49
    akka
    0.49
    POSITIVE LOGITS
     ticks
    0.46
     im
    0.45
    ticks
    0.44
    tick
    0.42
    jol
    0.41
     الرب
    0.41
     تث
    0.41
     Carr
    0.40
    cron
    0.40
     Gub
    0.38
    Activations Density 0.002%

    No Known Activations