© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5750
    Prev
    Next
    INDEX
    Explanations

    instances of the words "gold" and "chain"

    oai_token-act-pair · gemini-2.0-flash

    supply chains or colloidal gold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.49
     a
    -0.43
     Greene
    -0.42
    برا
    -0.42
     be
    -0.41
     an
    -0.41
    ific
    -0.40
     refer
    -0.40
     Greg
    -0.40
     feel
    -0.39
    POSITIVE LOGITS
    ########.
    1.02
    yntaxException
    0.99
    躇
    0.96
    ंदीखरीदारी
    0.94
    IsMutable
    0.92
     wireType
    0.92
    AddTagHelper
    0.88
     oprot
    0.86
    ArgsConstructor
    0.85
    thâu
    0.85
    Activations Density 0.047%

    No Known Activations