© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158235
    Prev
    Next
    INDEX
    Explanations

    say "team"

    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
     purs
    0.42
    zarchiwizowane
    0.40
     составля
    0.38
    沈
    0.36
     Lemb
    0.36
    Dan
    0.36
     לס
    0.35
     опро
    0.35
    ીએ
    0.35
    LabelTool
    0.35
    POSITIVE LOGITS
     W
    0.89
     Y
    0.72
    W
    0.64
    Y
    0.55
     Yan
    0.54
     डब्ल्यू
    0.52
     Pat
    0.51
    Yan
    0.49
     Ye
    0.48
     Yoo
    0.46
    Activations Density 0.007%

    No Known Activations