© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15423
    Prev
    Next
    INDEX
    Explanations

    terms related to ongoing research and development

    oai_token-act-pair · gemini-2.0-flash

    Progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    UnusedPrivate
    -0.80
     AssemblyProduct
    -0.77
     فريبيس
    -0.75
    UserScript
    -0.68
    aarrggbb
    -0.66
     Мексичка
    -0.65
    MockBean
    -0.65
    SpringBootTest
    -0.65
     itſelf
    -0.65
    تقاوى
    -0.65
    POSITIVE LOGITS
    よいよ
    0.46
    Date
    0.45
    Gön
    0.45
    }}],
    0.44
    hees
    0.44
    Listeners
    0.44
    `:
    0.43
     Stations
    0.43
    жают
    0.42
     Son
    0.42
    Activations Density 8.780%

    No Known Activations