© 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. 12542
    Prev
    Next
    INDEX
    Explanations

    hexadecimal representations related to hardware

    oai_token-act-pair · gemini-2.0-flash

    lx

    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
    MessageTagHelper
    -0.89
    LookAnd
    -0.78
     htons
    -0.63
    LabelTagHelper
    -0.58
    ArgsConstructor
    -0.57
    <bos>
    -0.54
    OGND
    -0.54
     kaarangay
    -0.53
    المشاركات
    -0.52
    InstrumentedTest
    -0.52
    POSITIVE LOGITS
    grand
    0.64
     totale
    0.60
     grand
    0.58
     setTotal
    0.56
     Wikidata
    0.54
     longue
    0.53
    dau
    0.53
    adze
    0.53
    lateinit
    0.53
     totals
    0.53
    Activations Density 2.853%

    No Known Activations