© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12872
    Prev
    Next
    INDEX
    Explanations

    numerical digits and special characters alone on a line

    oai_token-act-pair · gemini-2.0-flash

    system software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    toMatchSnapshot
    -0.49
    tanleria
    -0.44
     AssemblyVersion
    -0.42
     Pollack
    -0.42
    الصفحه
    -0.42
    GEBURTS
    -0.40
    ™
    -0.40
    AnimationsModule
    -0.40
    ظة
    -0.39
    amo
    -0.38
    POSITIVE LOGITS
    SequentialGroup
    0.84
    GraphicsUnit
    0.72
     Baillargeon
    0.69
    setVerticalGroup
    0.65
    Décès
    0.65
    enumi
    0.63
    bnf
    0.63
     anzuzeigen
    0.61
    oneer
    0.60
     corrector
    0.60
    Activations Density 4.042%

    No Known Activations