© 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. 11368
    Prev
    Next
    INDEX
    Explanations

    scounds, math formulas, variable assignments, and page numbers

    oai_token-act-pair · gemini-2.0-flash

    code/math text

    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
     real
    -0.42
     reales
    -0.41
    AndroidJUnit
    -0.40
    )][
    -0.39
    kezi
    -0.38
    getReal
    -0.37
    })^
    -0.37
    >[]
    -0.36
    )))));
    -0.36
    },[
    -0.36
    POSITIVE LOGITS
     autorytatywna
    1.06
     ExecuteAsync
    0.72
     kaarangay
    0.71
    IndentedString
    0.66
    PreferredItem
    0.66
    parsedMessage
    0.65
     Administrativna
    0.64
     AssemblyCulture
    0.63
    Vidite
    0.63
    بوابة
    0.63
    Activations Density 1.499%

    No Known Activations