© 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. 1216
    Prev
    Next
    INDEX
    Explanations

    instances of somebody or something being welcomed or received

    oai_token-act-pair · gemini-2.0-flash

    welcome messages

    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
     welcome
    -2.98
     Welcome
    -2.75
    welcome
    -2.61
     WELCOME
    -2.55
    Welcome
    -2.53
     welcomed
    -2.50
     welcoming
    -2.41
    WELCOME
    -2.27
     welcomes
    -2.27
     bienvenida
    -1.80
    POSITIVE LOGITS
    addPreferredGap
    0.59
     оригіналу
    0.56
    styleUrls
    0.55
    发表于
    0.53
     Highland
    0.51
     jScrollPane
    0.50
    Portály
    0.50
    enumii
    0.50
    prnewswire
    0.48
    Merkmale
    0.47
    Activations Density 1.675%

    No Known Activations