© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3948
    Prev
    Next
    INDEX
    Explanations

    defining words/origins

    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_39_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
    [multimodal]
    0.34
     сде
    0.33
     asalamualaikum
    0.32
     bijective
    0.31
    ائز
    0.30
    拃
    0.30
     及び
    0.30
    オブジェクト
    0.30
     እየሱስ
    0.30
     TouchUtils
    0.30
    POSITIVE LOGITS
    h
    0.36
     w
    0.32
    we
    0.30
    w
    0.30
    le
    0.30
    ether
    0.29
    -
    0.29
    sw
    0.29
     kn
    0.28
    ho
    0.28
    Activations Density 0.055%

    No Known Activations