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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 477
    Prev
    Next
    INDEX
    Explanations

    loss, objective, criterion

    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_38_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
     nib
    0.40
     মন্
    0.39
    ***************
    0.37
     Geographical
    0.36
    ーパー
    0.36
    Refresh
    0.36
     pca
    0.36
     режисс
    0.35
    "`
    0.35
    quen
    0.35
    POSITIVE LOGITS
     loss
    0.84
    loss
    0.80
    损失
    0.80
    Loss
    0.79
     objective
    0.77
     Loss
    0.77
    損失
    0.76
    objective
    0.75
     perte
    0.72
    criterion
    0.71
    Activations Density 0.029%

    No Known Activations