© 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. 9641
    Prev
    Next
    INDEX
    Explanations

    words related to implementing a study or strategies to improve a situation

    oai_token-act-pair · gemini-2.0-flash

    evaluation

    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
    tagHelperRunner
    -0.82
    twimg
    -0.78
    BeginInit
    -0.71
    ThroughAttribute
    -0.67
    UnsafeEnabled
    -0.67
    脚注の使い方
    -0.66
    memoized
    -0.65
    intios
    -0.64
     autorytatywna
    -0.64
    Geplaatst
    -0.64
    POSITIVE LOGITS
     evaluation
    1.95
     Evaluation
    1.77
    Evaluation
    1.75
     evaluations
    1.66
     evaluated
    1.66
     EVALUATION
    1.63
     evaluate
    1.62
    evaluation
    1.62
     Evaluations
    1.55
     evaluating
    1.53
    Activations Density 2.111%

    No Known Activations