© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1020
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conditional advice.

    oai_token-act-pair · gemini-2.0-flash

    say "course" or personal pronoun

    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
    ")){
    -0.33
    ")){
    
    -0.33
    .";
    
    -0.32
    .")]
    -0.32
    )){
    
    -0.32
    **
    
    -0.31
    ).\
    -0.29
    )}</
    -0.29
    EXECUTIVE
    -0.29
    ()){
    
    -0.28
    POSITIVE LOGITS
     Together
    0.87
     They
    0.87
     Others
    0.86
     It
    0.84
     Again
    0.83
     That
    0.82
     There
    0.81
     About
    0.81
     africains
    0.80
     Things
    0.80
    Activations Density 36.111%

    No Known Activations