© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    instances of data collection and the ethics thereof

    oai_token-act-pair · gemini-2.0-flash

    collections of things

    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
     collection
    -2.50
     Collection
    -2.47
     collect
    -2.45
     collecting
    -2.44
     collected
    -2.44
     Collections
    -2.42
     collections
    -2.42
     Collecting
    -2.41
    Collection
    -2.39
     Collect
    -2.39
    POSITIVE LOGITS
    ug
    0.40
    Hos
    0.38
     hood
    0.37
    omorphology
    0.37
     Hos
    0.35
    UG
    0.35
     domes
    0.33
    ษ
    0.33
    Dru
    0.33
    RU
    0.33
    Activations Density 2.148%

    No Known Activations