© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2758
    Prev
    Next
    INDEX
    Explanations

    words related to addressing or references like URLs and IPs

    oai_token-act-pair · gemini-2.0-flash

    point

    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
     propOrder
    -0.71
    Autoritní
    -0.62
    IsMutable
    -0.56
    oa̍t
    -0.56
    StructEnd
    -0.56
    MLLoader
    -0.55
    __*/
    -0.54
    wikimedia
    -0.54
    AccessFile
    -0.54
    titleMargin
    -0.53
    POSITIVE LOGITS
     point
    3.16
     points
    3.00
    point
    2.72
     Points
    2.69
     Point
    2.66
    points
    2.59
    Point
    2.56
     POINT
    2.50
    Points
    2.48
     POINTS
    2.31
    Activations Density 7.164%

    No Known Activations