© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16134
    Prev
    Next
    INDEX
    Explanations

    gradient descent loss

    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_40_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
    Bp
    0.46
    BP
    0.45
     BP
    0.45
     bp
    0.43
     gradient
    0.43
     Radial
    0.42
     Gradient
    0.39
    偏
    0.39
    bp
    0.38
     conjugate
    0.38
    POSITIVE LOGITS
     loss
    0.55
    loss
    0.50
    Loss
    0.49
     LOSS
    0.49
     perdita
    0.48
    batch
    0.47
    批
    0.46
     Loss
    0.46
     Batch
    0.45
     val
    0.45
    Activations Density 0.146%

    No Known Activations