© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14635
    Prev
    Next
    INDEX
    Explanations

    occurrences of the form "on a" or "a" followed by an adjective

    oai_token-act-pair · gemini-2.0-flash

    entities or references to objects and items

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     direction
    -0.67
    direction
    -0.65
     directions
    -0.63
    seamnă
    -0.63
    directions
    -0.62
    LEncoder
    -0.57
     Direction
    -0.57
    matchCondition
    -0.56
     समीक्षाओं
    -0.55
    NOPQRST
    -0.54
    POSITIVE LOGITS
    tagHelperRunner
    0.63
    swire
    0.49
     couch
    0.46
    퀀
    0.46
     للمعارف
    0.46
     sto
    0.44
    DockStyle
    0.43
     BufferedImage
    0.43
    transQ
    0.43
     sofa
    0.42
    Activations Density 1.723%

    No Known Activations