© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12385
    Prev
    Next
    INDEX
    Explanations

    titles held by a person or organization

    oai_token-act-pair · gemini-2.0-flash

    utter statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ProtoMessage
    -1.00
     <=",
    -0.99
    RegressionTest
    -0.96
    DoubleQuotes
    -0.84
    EDEFAULT
    -0.82
    Tikang
    -0.77
    nemia
    -0.76
    GenerationType
    -0.76
    endphp
    -0.75
    tanleria
    -0.73
    POSITIVE LOGITS
    SqlParameter
    0.42
    vá
    0.39
    inquirer
    0.39
    구
    0.39
    joc
    0.39
    iches
    0.37
     ceramica
    0.36
     кампа
    0.36
     každ
    0.35
     all
    0.35
    Activations Density 2.929%

    No Known Activations