© 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. 37001
    Prev
    Next
    INDEX
    Explanations

    Sundar Pichai

    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
    ד
    0.86
    س
    0.80
    ek
    0.79
    j
    0.76
    ش
    0.76
    ח
    0.74
    ס
    0.74
    ג
    0.73
     to
    0.73
    K
    0.72
    POSITIVE LOGITS
    </h3>
    0.76
    atories
    0.68
    ulaires
    0.65
    :
    0.65
     necessidades
    0.64
    یس
    0.64
    labeled
    0.64
    山区
    0.64
    логи
    0.62
    нда
    0.62
    Activations Density 0.001%

    No Known Activations