© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7612
    Prev
    Next
    INDEX
    Explanations

    mentions of loss in general.

    oai_token-act-pair · gemini-2.0-flash

    loss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Kooper
    -0.45
    ectar
    -0.44
    jimo
    -0.42
    cle
    -0.41
    InteropServices
    -0.41
    kaner
    -0.41
    /@
    -0.41
    clé
    -0.40
     pseudos
    -0.40
     AssemblyProduct
    -0.40
    POSITIVE LOGITS
     loss
    2.34
     lost
    2.16
    Loss
    2.09
     Loss
    2.08
    loss
    2.02
     losses
    1.97
     LOSS
    1.96
    LOSS
    1.91
    lost
    1.88
    Lost
    1.84
    Activations Density 1.233%

    No Known Activations