© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5285
    Prev
    Next
    INDEX
    Explanations

    text with excessive hyphen usage or numbers in scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    parsedMessage
    -0.92
    fjspx
    -0.85
    tagHelperRunner
    -0.84
     CreateTagHelper
    -0.79
    ViewFeatures
    -0.77
    WithIOException
    -0.75
     NSCoder
    -0.72
    complexContent
    -0.72
    GraphicsUnit
    -0.70
    mybatisplus
    -0.70
    POSITIVE LOGITS
    To
    0.41
    Run
    0.36
    Or
    0.36
    Able
    0.35
    Than
    0.35
    Se
    0.35
    Aware
    0.35
    Set
    0.34
    In
    0.34
    On
    0.34
    Activations Density 8.386%

    No Known Activations