© 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. 5900
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to health and medical advice about virus and infection.

    oai_token-act-pair · gemini-2.0-flash

    Chemical substances and patents

    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
    ThroughAttribute
    -0.50
    chaun
    -0.50
    ="#"><
    -0.50
    itinéraire
    -0.48
    ,
    -0.47
    gonic
    -0.47
    ]</
    -0.46
    )";
    -0.45
     QWidget
    -0.45
     *)&
    -0.45
    POSITIVE LOGITS
    expandindo
    0.80
    DispatchToProps
    0.59
    setopt
    0.59
    writeFieldEnd
    0.56
     initWithFrame
    0.55
     protoimpl
    0.54
    makeText
    0.53
    RequiresApi
    0.52
    GMENT
    0.52
    Билгалдахарш
    0.52
    Activations Density 7.154%

    No Known Activations