© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5228
    Prev
    Next
    INDEX
    Explanations

    words commonly found in TV product reviews

    oai_token-act-pair · gemini-2.0-flash

    Media streaming devices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    مقاله
    -0.53
     DbSet
    -0.52
    Bibliograf
    -0.48
    blurRadius
    -0.48
     facteur
    -0.48
    viles
    -0.47
     كره
    -0.46
     panel
    -0.45
     MainAxisSize
    -0.45
    itore
    -0.44
    POSITIVE LOGITS
    LogFactory
    0.65
    antd
    0.61
     MaterialApp
    0.60
    Personensuche
    0.59
    mybatisplus
    0.57
    InteropServices
    0.57
    awtextra
    0.55
    UnusedPrivate
    0.54
    mtrl
    0.54
    XmlIgnore
    0.54
    Activations Density 2.792%

    No Known Activations