© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12811
    Prev
    Next
    INDEX
    Explanations

    words related to events that have been written about for a report

    oai_token-act-pair · gemini-2.0-flash

    words related to reporting incidents

    np_token-act-pair-logits · gpt-4o-mini

    report

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IsContent
    -0.48
    kus
    -0.45
    Demografía
    -0.43
    الإنجليزية
    -0.41
    piece
    -0.40
    [*
    -0.40
    ultar
    -0.40
     kawa
    -0.38
    δα
    -0.38
     pieces
    -0.38
    POSITIVE LOGITS
     report
    1.24
     reports
    1.02
    report
    1.00
     reporta
    0.96
     REPORT
    0.90
     reporte
    0.90
     Report
    0.89
    reports
    0.88
     Repo
    0.88
     Rept
    0.87
    Activations Density 1.274%

    No Known Activations