© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14412
    Prev
    Next
    INDEX
    Explanations

    words associated with writing and art, and negative sentiments about people taking advantage of others.

    oai_token-act-pair · gemini-2.0-flash

    Artists and writers

    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
    CloseOperation
    -0.86
    InjectAttribute
    -0.84
    styleType
    -0.72
    JspWriter
    -0.71
     celebrity
    -0.70
    __':
    -0.69
     Celebrity
    -0.68
    Famous
    -0.66
     famous
    -0.64
    Celebrity
    -0.64
    POSITIVE LOGITS
    Play
    0.48
    play
    0.47
     Layton
    0.46
     Play
    0.46
     play
    0.45
    supset
    0.44
    ség
    0.43
    ㅜ
    0.43
     Initialize
    0.43
     $_"
    0.42
    Activations Density 3.709%

    No Known Activations