© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11724
    Prev
    Next
    INDEX
    Explanations

    indented code blocks, numbered answers, or bracketed text

    oai_token-act-pair · gemini-2.0-flash

    Code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    uxxxx
    -0.51
    ↵↵
    -0.48
    .
    -0.45
    -
    -0.45
     con
    -0.45
     F
    -0.45
     res
    -0.42
    <
    -0.42
    ,
    -0.42
    *
    -0.42
    POSITIVE LOGITS
     itſelf
    0.91
     raiſ
    0.89
    StoreMessageInfo
    0.88
     AssemblyTitle
    0.85
     disambiguazione
    0.84
     ſte
    0.83
     propOrder
    0.83
     Monfieur
    0.82
     ujednoznacz
    0.79
     houſe
    0.79
    Activations Density 0.042%

    No Known Activations