© 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. 900
    Prev
    Next
    INDEX
    Explanations

    text describing puzzles and games for children

    oai_token-act-pair · gemini-2.0-flash

    Technical processes

    np_max-act-logits · 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
    contentLoaded
    -0.75
    findpost
    -0.62
    ंदीखरीदारी
    -0.61
     doubtnut
    -0.60
    InjectAttribute
    -0.60
     Efq
    -0.60
    Personensuche
    -0.59
    ómicos
    -0.59
    談社
    -0.57
     eenig
    -0.56
    POSITIVE LOGITS
    URLEncoder
    0.52
    érôme
    0.51
    olus
    0.49
    rita
    0.48
    |$
    0.48
    renti
    0.48
    appcompat
    0.48
    று
    0.48
    ANGA
    0.47
     deb
    0.47
    Activations Density 2.782%

    No Known Activations