© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10577
    Prev
    Next
    INDEX
    Explanations

    words and phrases used when discussing food, especially in restaurant reviews

    oai_token-act-pair · gemini-2.0-flash

    Mixed language terms and jargon

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

    food reviews

    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
    enderror
    -0.61
     kasarigan
    -0.58
    AFX
    -0.55
     Sociales
    -0.52
     communs
    -0.52
    près
    -0.51
     circulaire
    -0.49
    inout
    -0.48
     pellic
    -0.48
     Theſe
    -0.47
    POSITIVE LOGITS
     nawr
    0.66
     parcel
    0.58
    migrationBuilder
    0.57
     الرياضيه
    0.54
    proper
    0.54
    Espèce
    0.54
     RRP
    0.53
     INVENTION
    0.53
     meneg
    0.52
    extAlignment
    0.52
    Activations Density 0.872%

    No Known Activations