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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8650
    Prev
    Next
    INDEX
    Explanations

    words from technical online sales documents, including VPNs, software, and hardware.

    oai_token-act-pair · gemini-2.0-flash

    line

    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
     variety
    -0.68
     INTERESAR
    -0.66
     variété
    -0.58
    évaluateur
    -0.56
    variety
    -0.56
    __).
    -0.54
    iedział
    -0.54
     Variety
    -0.54
     main
    -0.54
     variedad
    -0.54
    POSITIVE LOGITS
     fieldNum
    0.70
    makeConstraints
    0.55
     perform
    0.50
    :✨
    0.48
     Perform
    0.47
     defaultstate
    0.47
    IUrlHelper
    0.47
     BorderRadius
    0.46
    occasion
    0.45
    routeProvider
    0.45
    Activations Density 0.632%

    No Known Activations