© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11971
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to emotions in different situations and events.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     OFDb
    -0.63
     '\\;'
    -0.61
     Италијани
    -0.55
    %");
    -0.50
    aarrggbb
    -0.49
     GeoNames
    -0.47
     betweenstory
    -0.46
     Și
    -0.46
    glers
    -0.46
    borne
    -0.45
    POSITIVE LOGITS
    ReusableCell
    0.63
    ArgumentParser
    0.60
    +#+#
    0.60
    gwt
    0.59
     acceptez
    0.59
    flink
    0.58
    mybatisplus
    0.55
     onlyOwner
    0.55
    ArgsConstructor
    0.54
    Hochspringen
    0.54
    Activations Density 1.304%

    No Known Activations