© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2552
    Prev
    Next
    INDEX
    Explanations

    the word "feature" and related words

    oai_token-act-pair · gemini-2.0-flash

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     feature
    -2.61
     features
    -2.56
    features
    -2.30
    feature
    -2.28
     Features
    -2.25
    Feature
    -2.22
    Features
    -2.20
     Feature
    -2.19
     FEATURE
    -1.88
     FEATURES
    -1.88
    POSITIVE LOGITS
    BeginInit
    0.88
     CreateTagHelper
    0.84
    parsedMessage
    0.82
    BeginContext
    0.79
    Hauptartikel
    0.75
     TestBed
    0.71
    Према
    0.69
    الإنجليزية
    0.68
     ControllerBase
    0.66
    ParallelGroup
    0.66
    Activations Density 3.152%

    No Known Activations