© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    periods followed by single-digit numbers

    oai_token-act-pair · gemini-2.0-flash

    say "methods/properties in code"

    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
    ">//
    -0.89
     nahilalakip
    -0.81
    rungsseite
    -0.77
    runApp
    -0.75
    ]*(
    -0.75
     transfieras
    -0.74
    \}\\
    -0.74
     "];
    -0.73
    endphp
    -0.73
    ]--;
    -0.73
    POSITIVE LOGITS
    getvalue
    0.41
    ↵
    0.40
    moveToFirst
    0.39
    vnd
    0.38
    ItemBackground
    0.38
    intValue
    0.37
     regras
    0.37
     get
    0.36
    Surprisingly
    0.35
    argmax
    0.35
    Activations Density 0.737%

    No Known Activations