© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11837
    Prev
    Next
    INDEX
    Explanations

    the word "loss" within a technical scientific document

    oai_token-act-pair · gemini-2.0-flash

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loss
    -2.77
     Loss
    -2.42
    loss
    -2.42
    Loss
    -2.30
     LOSS
    -2.00
     losses
    -1.77
    LOSS
    -1.75
     Losses
    -1.57
     pérdida
    -1.53
    losses
    -1.51
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.67
     HasFactory
    0.60
     Reverso
    0.58
    multer
    0.56
    WebElementEntity
    0.53
    hept
    0.52
    openzeppelin
    0.50
    consulté
    0.48
     resourceCulture
    0.48
     Solver
    0.48
    Activations Density 0.898%

    No Known Activations