© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1230
    Prev
    Next
    INDEX
    Explanations

    URLs, specifically those starting with "http"

    oai_token-act-pair · gemini-2.0-flash

    http

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '\\;'
    -1.01
    IGraphics
    -0.79
    rungsseite
    -0.76
     jadx
    -0.73
     contextLoads
    -0.71
    UnknownFields
    -0.69
    TargetException
    -0.69
     Weibo
    -0.69
    ObjectContext
    -0.68
    titleMargin
    -0.68
    POSITIVE LOGITS
    v
    0.53
     s
    0.45
    ss
    0.40
     ujednoznacz
    0.40
     v
    0.40
    apiVersion
    0.40
     e
    0.39
    \_
    0.38
    ále
    0.36
    gow
    0.35
    Activations Density 0.224%

    No Known Activations