© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14772
    Prev
    Next
    INDEX
    Explanations

    words related to software updates and software development

    oai_token-act-pair · gemini-2.0-flash

    features

    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
     naselje
    -0.47
    änden
    -0.43
    vå
    -0.43
     BorderRadius
    -0.43
    classmethod
    -0.42
     crun
    -0.42
     assent
    -0.41
    ndra
    -0.41
    irnov
    -0.40
    الإنجليزية
    -0.40
    POSITIVE LOGITS
     features
    2.30
     feature
    2.14
     Features
    2.05
    features
    2.02
    feature
    1.97
     Feature
    1.91
    Features
    1.91
    Feature
    1.86
     FEATURES
    1.78
     FEATURE
    1.71
    Activations Density 3.165%

    No Known Activations