© 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. 11613
    Prev
    Next
    INDEX
    Explanations

    proper names or words that could be proper names

    oai_token-act-pair · gemini-2.0-flash

    Legal case names and citations

    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
     snippetHide
    -1.05
     kaarangay
    -0.84
    sizeCache
    -0.77
    oa̍t
    -0.74
    LookAnd
    -0.72
     betweenstory
    -0.67
    posedge
    -0.67
     فريبيس
    -0.67
    IndentedString
    -0.66
    Portail
    -0.66
    POSITIVE LOGITS
    เอง
    0.52
    seamnă
    0.48
     gjerne
    0.42
    leştir
    0.38
     læng
    0.38
    nyttet
    0.36
    hling
    0.36
    يش
    0.36
    自己是
    0.36
    *@
    0.35
    Activations Density 5.016%

    No Known Activations