© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12495
    Prev
    Next
    INDEX
    Explanations

    words related to joy, humour and smiling/laughing

    oai_token-act-pair · gemini-2.0-flash

    instances of laughter and humor

    np_token-act-pair-logits · gpt-4o-mini

    laugh

    np_max-act-logits · gemini-2.0-flash
    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
    LookAnd
    -0.73
     jScrollPane
    -0.69
    tagHelperRunner
    -0.68
    SourceChecksum
    -0.62
    ########.
    -0.60
    hazi
    -0.58
    TargetException
    -0.57
    bledon
    -0.56
     capito
    -0.55
    iotensin
    -0.55
    POSITIVE LOGITS
    Билгалдахарш
    0.56
    謡
    0.46
     Stork
    0.46
    PYX
    0.46
     mapStateToProps
    0.45
    出版年
    0.45
    HandleFunc
    0.44
    VersionUID
    0.44
     Gewerks
    0.43
    EndTag
    0.41
    Activations Density 2.269%

    No Known Activations