© 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-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9820
    Prev
    Next
    INDEX
    Explanations

    the word "loss" and words associated with financial success and failure

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    -3.17
     Loss
    -2.94
    Loss
    -2.88
    loss
    -2.77
     LOSS
    -2.56
     losses
    -2.42
    LOSS
    -2.33
     Losses
    -2.20
     perte
    -2.05
     lose
    -2.03
    POSITIVE LOGITS
     resourceCulture
    0.61
     Roskov
    0.58
    himovic
    0.55
     }}"></
    0.53
    ftagPool
    0.50
    REET
    0.49
    UAGES
    0.45
    onViewCreated
    0.45
    gée
    0.45
    mdb
    0.45
    Activations Density 0.490%

    No Known Activations