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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3076
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate surprise, annoyance, appreciation, or other sentiment.

    oai_token-act-pair · 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
     So
    -2.56
    So
    -2.36
    SO
    -2.00
     SO
    -1.98
    so
    -1.87
    Sooo
    -1.34
     sooo
    -1.20
     sooooo
    -1.20
     所以
    -1.19
     soooo
    -1.18
    POSITIVE LOGITS
     cinturón
    0.50
    Clik
    0.49
    tics
    0.47
    prepareStatement
    0.44
    uzi
    0.43
    busch
    0.43
    helial
    0.42
    sweetalert
    0.41
     saites
    0.41
    ęgn
    0.41
    Activations Density 4.497%

    No Known Activations