© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10669
    Prev
    Next
    INDEX
    Explanations

    words related to food and cuisine

    oai_token-act-pair · gemini-2.0-flash

    food and cooking

    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
    tvguidetime
    -0.88
     Chriftian
    -0.84
     Efq
    -0.81
    ритори
    -0.78
    makeConstraints
    -0.78
     Theſe
    -0.77
     ſeveral
    -0.77
     leaſt
    -0.76
     iſt
    -0.75
     Eſ
    -0.74
    POSITIVE LOGITS
     kasarigan
    0.66
     paik
    0.46
    Билгалдахарш
    0.43
    MigrationBuilder
    0.42
     humo
    0.40
     voeten
    0.39
     aç
    0.38
    /
    0.38
     frutas
    0.37
     tabaco
    0.37
    Activations Density 1.500%

    No Known Activations