© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14966
    Prev
    Next
    INDEX
    Explanations

    words and expressions from various scientific fields, especially biology, genetics, and chemistry

    oai_token-act-pair · gemini-2.0-flash

    scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    al
    -1.78
    als
    -1.61
    AL
    -1.60
    all
    -1.36
    ales
    -1.33
    ALS
    -1.33
    ality
    -1.30
    ale
    -1.27
    ally
    -1.26
    aler
    -1.25
    POSITIVE LOGITS
    GOTREF
    0.65
    parsedMessage
    0.63
    homonymie
    0.60
     تضيفلها
    0.55
     виправивши
    0.53
     disponibilités
    0.52
    GEBURTS
    0.48
    ندران
    0.47
    anskje
    0.47
    Autoritní
    0.47
    Activations Density 4.727%

    No Known Activations