© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43073
    Prev
    Next
    INDEX
    Explanations

    machinations, Ex Machina

    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_3_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
    I
    0.97
    o
    0.89
    V
    0.83
    "
    0.82
    T
    0.82
    C
    0.81
    S
    0.78
    P
    0.77
    W
    0.75
    ו
    0.75
    POSITIVE LOGITS
     phonons
    0.75
    ח
    0.73
     spéciales
    0.72
     appareils
    0.71
     complic
    0.68
     centrales
    0.68
     sequels
    0.68
    مر
    0.67
    ké
    0.67
     сфор
    0.67
    Activations Density 0.000%

    No Known Activations