© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5179
    Prev
    Next
    INDEX
    Explanations

    words or sentence components that are part of polite conversation

    oai_token-act-pair · gemini-2.0-flash

    greetings and honorifics

    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
     folks
    -0.97
    Folks
    -0.82
     Folks
    -0.81
     dear
    -0.74
    Dear
    -0.68
     Dear
    -0.66
    dear
    -0.66
     gentlemen
    -0.64
     fellas
    -0.62
     señor
    -0.61
    POSITIVE LOGITS
     vägen
    0.82
     varandra
    0.66
    HostException
    0.65
     démocr
    0.62
    tagez
    0.57
     preuves
    0.56
    
    0.56
     igenom
    0.55
     Савезне
    0.55
     despe
    0.55
    Activations Density 2.738%

    No Known Activations