© 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. 3489
    Prev
    Next
    INDEX
    Explanations

    restaurant names

    oai_token-act-pair · gemini-2.0-flash

    restaurant names and 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_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
    Personendaten
    -0.73
    Enllaces
    -0.64
     estekak
    -0.63
     saites
    -0.62
     Wicidata
    -0.62
    spunk
    -0.60
    Література
    -0.57
    Kjelder
    -0.55
     مشين
    -0.54
    Zunanje
    -0.54
    POSITIVE LOGITS
    <?,
    0.52
    +:+
    0.49
    nameLabel
    0.48
    modelBuilder
    0.46
    ليق
    0.45
    Gruppen
    0.45
     Pâ
    0.44
    InstanceState
    0.44
    withIdentifier
    0.44
     hoofd
    0.43
    Activations Density 8.557%

    No Known Activations