© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8844
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest exception or failure

    oai_token-act-pair · gemini-2.0-flash

    inclusion and exclusion

    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
    Sdk
    -0.52
     Lij
    -0.47
    concat
    -0.46
     Format
    -0.44
     included
    -0.43
     članak
    -0.43
    kli
    -0.42
    ouren
    -0.42
    dou
    -0.42
    直
    -0.42
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.72
    AsUp
    0.71
    DockStyle
    0.71
    ConstraintMaker
    0.70
    InjectAttribute
    0.69
     BoxDecoration
    0.67
    RegistryLite
    0.66
    )";
    0.64
     препратки
    0.64
    .";
    0.64
    Activations Density 1.455%

    No Known Activations