© 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. 35990
    Prev
    Next
    INDEX
    Explanations

    aircraft aviation

    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
     tied
    0.45
    ตร
    0.43
    tied
    0.43
    𝕟
    0.42
    에요
    0.40
    Substitution
    0.38
     Bola
    0.37
     tine
    0.37
     basa
    0.37
     bola
    0.37
    POSITIVE LOGITS
     cult
    0.42
     listener
    0.39
     سرد
    0.39
    SCHRAMM
    0.38
    鵡
    0.38
     му
    0.37
    bord
    0.36
     எண்ணெய்
    0.36
    務
    0.36
     jump
    0.35
    Activations Density 0.001%

    No Known Activations