© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8568
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing aversion, obligation, or future intent with "will" or "would" and negative contractions

    oai_token-act-pair · gemini-2.0-flash

    Expressing disbelief or choice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     HasFactory
    -0.81
    printStackTrace
    -0.78
    存于互联网档案馆
    -0.69
    <?
    -0.65
    NgModule
    -0.64
     ***!
    -0.61
    UpInside
    -0.60
    DebuggerNonUser
    -0.60
     consultato
    -0.59
     MatDialog
    -0.57
    POSITIVE LOGITS
    Rüyada
    0.73
     care
    0.61
     sign
    0.54
     last
    0.52
    EndProject
    0.51
     contra
    0.51
     try
    0.50
     win
    0.50
    uarine
    0.49
    ıç
    0.49
    Activations Density 5.045%

    No Known Activations