© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14584
    Prev
    Next
    INDEX
    Explanations

    text discussing learning from mistakes and reviews of failures

    oai_token-act-pair · gemini-2.0-flash

    learning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     \%$\\
    -0.49
    AddTagHelper
    -0.47
    UserScript
    -0.45
    tamol
    -0.45
    hdashline
    -0.43
    XmlAccessType
    -0.41
    EntityFramework
    -0.40
    passphrase
    -0.40
    blica
    -0.40
    RATES
    -0.40
    POSITIVE LOGITS
     learning
    3.00
     learn
    2.95
     learns
    2.72
     Learning
    2.70
     learned
    2.69
    learn
    2.61
    learning
    2.59
    Learning
    2.56
     Learn
    2.52
     learnt
    2.48
    Activations Density 2.097%

    No Known Activations