© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5051
    Prev
    Next
    INDEX
    Explanations

    words with strong emotional associations, including crude or harsh language

    oai_token-act-pair · gemini-2.0-flash

    Profanity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.09
     idéia
    -0.96
     daß
    -0.72
     muß
    -0.71
     favorably
    -0.66
     neighbors
    -0.66
     rumor
    -0.66
     rumors
    -0.65
    neighbors
    -0.64
     neighbor
    -0.64
    POSITIVE LOGITS
     specialises
    0.96
    arised
    0.94
    alised
    0.93
     prioritise
    0.92
    itisation
    0.92
     Organiser
    0.88
     onwards
    0.85
     finalised
    0.85
    ysing
    0.85
     specialising
    0.85
    Activations Density 1.608%

    No Known Activations