© 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. 36703
    Prev
    Next
    INDEX
    Explanations

    ADAS

    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
     conglomerate
    0.71
     heaped
    0.67
    เป็น
    0.66
     supernatants
    0.65
    ۔
    0.65
    5
    0.64
    е
    0.64
    は
    0.64
    จะ
    0.64
    پ
    0.64
    POSITIVE LOGITS
    (
    0.76
    art
    0.69
    ia
    0.66
    </h3>
    0.61
    at
    0.58
    .>
    0.58
     হয়তো
    0.57
    elu
    0.57
    ojen
    0.56
    </h2>
    0.55
    Activations Density 0.009%

    No Known Activations