© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3360
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "this", "the", "founding", "a", "my", "our", and select prepositions

    oai_token-act-pair · gemini-2.0-flash

    references to "country."

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     BoxFit
    -0.69
     Alligator
    -0.68
     gynhyrchwyd
    -0.64
     CGRectMake
    -0.63
    REDIT
    -0.62
    TypedDataSet
    -0.61
     saites
    -0.61
    Jegyzetek
    -0.60
     betale
    -0.60
     Bayes
    -0.59
    POSITIVE LOGITS
     country
    0.52
     Country
    0.42
    country
    0.40
    Country
    0.39
    脚注の使い方
    0.39
     >=",
    0.38
     standard
    0.38
     autorytatywna
    0.38
     kark
    0.37
    Collegamenti
    0.37
    Activations Density 0.836%

    No Known Activations