© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43698
    Prev
    Next
    INDEX
    Explanations

    Michael Scott, Microsoft Graph, Defender, Jordan

    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
    KHTML
    0.70
     येते
    0.63
    "
    0.63
    LDA
    0.63
    am
    0.61
    MAGIC
    0.56
    thought
    0.56
    A
    0.56
    くる
    0.55
    ப்படுகிறது
    0.55
    POSITIVE LOGITS
    ك
    0.77
    يا
    0.61
    ת
    0.60
    \
    0.59
     organismes
    0.58
     slaves
    0.58
    יות
    0.56
     esperado
    0.55
    nels
    0.55
     bushes
    0.55
    Activations Density 0.002%

    No Known Activations