© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13606
    Prev
    Next
    INDEX
    Explanations

    phrases that express location or belonging

    oai_token-act-pair · gemini-2.0-flash

    say "country"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     nation
    -1.40
     nations
    -1.35
     Countries
    -1.34
     COUNTRY
    -1.31
    COUNTRY
    -1.30
     Country
    -1.29
    Country
    -1.27
     country
    -1.26
     Nation
    -1.23
    country
    -1.19
    POSITIVE LOGITS
    pl
    0.43
     ako
    0.41
    <bos>
    0.40
    انگلیسی
    0.39
    Enllaces
    0.39
    Lähteet
    0.39
    DoubleQuotes
    0.38
     anglick
    0.38
    Reprints
    0.38
     partea
    0.38
    Activations Density 1.411%

    No Known Activations