© 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. 37600
    Prev
    Next
    INDEX
    Explanations

    Bob Johnson, Bob Ross tutorial

    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
    ದ
    0.70
    做
    0.70
    称
    0.66
    ről
    0.63
    大
    0.63
    كد
    0.63
    بغي
    0.62
     energized
    0.61
    يا
    0.61
    به
    0.61
    POSITIVE LOGITS
    "
    0.72
     componente
    0.69
    UM
    0.68
    ",
    0.63
     serupa
    0.63
     berwarna
    0.61
     sonuc
    0.60
    ail
    0.59
     berkaitan
    0.59
     pangan
    0.58
    Activations Density 0.002%

    No Known Activations