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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4041
    Prev
    Next
    INDEX
    Explanations

    scientific language for constructing a theory or algorithm

    oai_token-act-pair · gemini-2.0-flash

    Technical/Mathematical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    发表于
    -0.66
    ark
    -0.57
    NameInMap
    -0.56
     referenties
    -0.55
    arked
    -0.54
     ModelExpression
    -0.52
    DialogContent
    -0.52
     оригіналу
    -0.52
    oneofs
    -0.50
    ModelSerializer
    -0.50
    POSITIVE LOGITS
     upper
    0.66
    upper
    0.63
    writeFieldEnd
    0.60
     Stopping
    0.59
     mesures
    0.57
    TemporalType
    0.57
     measures
    0.56
     stopping
    0.55
    Measures
    0.55
     bounds
    0.55
    Activations Density 8.943%

    No Known Activations