© 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. 14989
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating changes or modifications

    oai_token-act-pair · gemini-2.0-flash

    Changes

    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
     Changes
    -2.38
     changes
    -2.33
     change
    -2.25
    changes
    -2.25
     Change
    -2.20
    Changes
    -2.16
    change
    -2.13
     CHANGES
    -2.11
    Change
    -2.09
     CHANGE
    -2.09
    POSITIVE LOGITS
     filles
    0.39
    CAPTION
    0.35
    auro
    0.35
     חיצוניים
    0.34
    tigheter
    0.34
     AssemblyCulture
    0.34
    ılığı
    0.34
    CHAPTER
    0.32
     fils
    0.31
    itemBuilder
    0.30
    Activations Density 1.738%

    No Known Activations