© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5063
    Prev
    Next
    INDEX
    Explanations

    academic or research papers that contain mathematical formulas, data, and analyses leading to conclusions

    oai_token-act-pair · gemini-2.0-flash

    that

    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
    Negative Logits
    ArrowToggle
    -0.57
    setof
    -0.48
     kính
    -0.47
    UnusedPrivate
    -0.44
    PageContext
    -0.43
    iel
    -0.43
     BitmapFactory
    -0.43
    Pres
    -0.43
     Trig
    -0.42
     kaynağından
    -0.42
    POSITIVE LOGITS
     الدولى
    0.71
     متعلقه
    0.63
    ungsbedingungen
    0.62
    ultuous
    0.61
    }{*}{}
    0.60
    ]")]
    0.59
    InstanceState
    0.58
    .*")]
    0.57
    awtextra
    0.57
     Holbrook
    0.55
    Activations Density 3.647%

    No Known Activations