© 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. 12942
    Prev
    Next
    INDEX
    Explanations

    words related to the applicability of results

    oai_token-act-pair · gemini-2.0-flash

    applicability

    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
    <bos>
    -0.81
     propOrder
    -0.76
     kasarigan
    -0.70
    MigrationBuilder
    -0.61
    principalTable
    -0.61
    BeginContext
    -0.60
    XmlAccessType
    -0.60
     PrintWriter
    -0.57
    RegisterType
    -0.56
    WebElementEntity
    -0.55
    POSITIVE LOGITS
     apply
    0.81
     applying
    0.76
     applied
    0.73
    apply
    0.72
    APPLY
    0.72
    Apply
    0.72
     Apply
    0.68
    applying
    0.68
    unnitel
    0.65
     APPLY
    0.65
    Activations Density 1.903%

    No Known Activations