© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2592
    Prev
    Next
    INDEX
    Explanations

    capitalized names of people

    oai_token-act-pair · gemini-2.0-flash

    crime and apprehension

    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
    AddTagHelper
    -0.71
    MigrationBuilder
    -0.70
    homonymie
    -0.62
    glMatrixMode
    -0.61
    IVEREF
    -0.61
    principalTable
    -0.60
    mapStateToProps
    -0.59
     millioner
    -0.58
    UnsafeEnabled
    -0.56
    rån
    -0.56
    POSITIVE LOGITS
    WriteBarrier
    0.54
    ForKey
    0.43
    void
    0.42
    Sent
    0.42
     Weak
    0.42
     Pairs
    0.41
    Pairs
    0.41
     Memo
    0.41
     Toma
    0.41
     SPS
    0.40
    Activations Density 0.570%

    No Known Activations