© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2083
    Prev
    Next
    INDEX
    Explanations

    deep neural network

    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
     firefighting
    0.45
    polarized
    0.42
    消防
    0.41
     firefighters
    0.41
    ⋄
    0.40
     सचिव
    0.40
    StatusCodes
    0.39
     polarized
    0.39
     busier
    0.39
     അധ
    0.38
    POSITIVE LOGITS
     Deep
    0.51
    딥
    0.50
     neural
    0.50
     Neural
    0.49
     deep
    0.46
    Deep
    0.46
    神经网络
    0.45
    deep
    0.44
    Neural
    0.41
    nn
    0.40
    Activations Density 0.345%

    No Known Activations