© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11122
    Prev
    Next
    INDEX
    Explanations

    words relating to public infrastructure, particularly bathrooms and train stations

    oai_token-act-pair · gemini-2.0-flash

    bathroom facilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     
    -0.45
    bilità
    -0.43
     po
    -0.43
    致
    -0.42
     खिला
    -0.39
     сла
    -0.39
     ob
    -0.39
     ust
    -0.38
    meria
    -0.38
    uben
    -0.38
    POSITIVE LOGITS
    SharedCtor
    0.96
    awtextra
    0.94
    पया
    0.93
     يتيمه
    0.89
    CodedInputStream
    0.84
    migrationBuilder
    0.80
    XmlAccessType
    0.79
    oredCriteria
    0.79
    Obrázky
    0.79
    aarrggbb
    0.79
    Activations Density 1.090%

    No Known Activations