© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9380
    Prev
    Next
    INDEX
    Explanations

    content that is politically charged, especially phrases expressing racial or political bias.

    oai_token-act-pair · gemini-2.0-flash

    geable

    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
    GraphicsUnit
    -0.83
     StringTokenizer
    -0.79
    GEBURTSDATUM
    -0.75
    WriteTagHelper
    -0.73
    
    -0.71
     Whigs
    -0.69
    tvguidetime
    -0.69
    InjectAttribute
    -0.68
    ImageContext
    -0.67
    Vidite
    -0.67
    POSITIVE LOGITS
    ieh
    0.48
    เพ
    0.44
    thest
    0.42
    garten
    0.41
     pemas
    0.41
    getLeft
    0.41
    stahl
    0.40
    Double
    0.40
     utiles
    0.40
     Useful
    0.39
    Activations Density 4.217%

    No Known Activations