© 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. 392
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technical product support, sales, or customer service

    oai_token-act-pair · gemini-2.0-flash

    support

    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
    saraba
    -0.50
     perche
    -0.44
    cerne
    -0.43
     Quail
    -0.43
     Initializes
    -0.40
     assurent
    -0.39
    UniformLocation
    -0.39
     DialogInterface
    -0.39
     createState
    -0.39
     střed
    -0.39
    POSITIVE LOGITS
     Meksiku
    0.84
     חיצוניים
    0.84
    []){
    0.78
    __":
    0.74
     ErrIntOverflow
    0.70
    parsedMessage
    0.69
    __':
    0.68
    ++
    0.67
    hdashline
    0.66
    __*/
    0.63
    Activations Density 29.801%

    No Known Activations