© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13772
    Prev
    Next
    INDEX
    Explanations

    references to slow movement in various contexts.

    oai_token-act-pair · gemini-2.0-flash

    slow

    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
     Slow
    -2.59
     slow
    -2.58
    Slow
    -2.56
    slow
    -2.47
     SLOW
    -2.31
     slower
    -2.22
     slowest
    -2.14
    SLOW
    -2.13
     slows
    -2.02
     slowing
    -1.95
    POSITIVE LOGITS
    XmlAccessType
    0.48
    Према
    0.43
    jsxFileName
    0.40
    atid
    0.39
     الو
    0.39
    ís
    0.38
    GHS
    0.38
     ọ
    0.37
    zzleHttp
    0.37
     bottes
    0.36
    Activations Density 1.983%

    No Known Activations