© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6609
    Prev
    Next
    INDEX
    Explanations

    a variety of patterns including code, URLs, ratios, and letter combinations

    oai_token-act-pair · gemini-2.0-flash

    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
    GraphicsUnit
    -0.63
     typelib
    -0.52
    ArgsConstructor
    -0.50
    onAttach
    -0.47
    Демографія
    -0.44
     lærer
    -0.44
    nonatomic
    -0.42
    PathVariable
    -0.41
     Persians
    -0.40
     ProtoMessage
    -0.40
    POSITIVE LOGITS
    tad
    0.79
     Wad
    0.77
    yad
    0.75
    Vad
    0.74
    BAD
    0.74
     BAD
    0.74
     Kud
    0.73
    aded
    0.73
     Jad
    0.73
    wad
    0.72
    Activations Density 5.111%

    No Known Activations