© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13187
    Prev
    Next
    INDEX
    Explanations

    the ends of sentances, single quotes, and numbers.

    oai_token-act-pair · gemini-2.0-flash

    punctuation and metadata indicators

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     <>",
    -0.58
     eget
    -0.47
     combineReducers
    -0.46
     Laboratories
    -0.44
    bukkit
    -0.44
     Mts
    -0.44
     pajero
    -0.43
    quelize
    -0.43
     lapsed
    -0.43
     ACI
    -0.43
    POSITIVE LOGITS
    IsContent
    0.67
     обращения
    0.64
    — 
    0.57
    astify
    0.57
     getItemCount
    0.55
    nościo
    0.54
    OfBirth
    0.53
    ISupport
    0.53
     onOptions
    0.53
     Процитовано
    0.52
    Activations Density 1.204%

    No Known Activations