© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4496
    Prev
    Next
    INDEX
    Explanations

    legal or medical non-compliance

    oai_token-act-pair · gemini-2.0-flash

    non-compliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rungsseite
    -0.76
    <bos>
    -0.66
    ंदीखरीदारी
    -0.63
     unknownFields
    -0.58
    Rè
    -0.57
    MigrationBuilder
    -0.57
     <<<<<<<<<<<<<<
    -0.56
    CppMethod
    -0.56
     المعرف
    -0.56
     InputDecoration
    -0.56
    POSITIVE LOGITS
    FailureListener
    0.56
    herme
    0.48
     collectivités
    0.47
    valbard
    0.47
    mería
    0.45
    AdapterView
    0.45
    oplayer
    0.43
    ExecuteReader
    0.43
    alisco
    0.42
    WritableDatabase
    0.42
    Activations Density 1.688%

    No Known Activations