© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227566
    Prev
    Next
    INDEX
    Explanations

    anticipate / anticipation

    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_6_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
    ↵↵
    1.06
    ிய
    0.85
    0.82
    0.82
    articolo
    0.81
     Abgerufen
    0.77
    ↵↵↵↵
    0.77
    ock
    0.77
    ピー
    0.75
     vardı
    0.75
    POSITIVE LOGITS
    ít
    0.95
    не
    0.86
    thet
    0.86
    ن
    0.84
    n
    0.84
    ע
    0.84
    the
    0.82
    λ
    0.80
     entendre
    0.79
    et
    0.79
    Activations Density 0.000%

    No Known Activations