© 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. 3500
    Prev
    Next
    INDEX
    Explanations

    mentions of people (age, gender, and nationality).

    oai_token-act-pair · gemini-2.0-flash

    People's Descriptions

    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
     skaters
    -0.67
    achers
    -0.66
    members
    -0.64
    oners
    -0.64
     members
    -0.63
     مشين
    -0.63
    ians
    -0.62
     capitalists
    -0.62
     swimmers
    -0.62
     residents
    -0.61
    POSITIVE LOGITS
     man
    1.13
    Man
    0.91
     Man
    0.90
     MAN
    0.77
    man
    0.76
    MAN
    0.65
     AssemblyVersion
    0.58
     كومونز
    0.56
     manto
    0.55
     mergeFrom
    0.55
    Activations Density 6.696%

    No Known Activations