© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    mentions of referring or being referred to, along with words indicating someone is doing something, like acting or being nominated

    oai_token-act-pair · gemini-2.0-flash

    referred

    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
    DockStyle
    -0.88
     propOrder
    -0.79
     "..\..\
    -0.79
     "..\..\..\
    -0.75
     pinulongan
    -0.74
    abestanden
    -0.74
     Roskov
    -0.73
    AutoScaleMode
    -0.72
    ArgsConstructor
    -0.71
    LookAnd
    -0.71
    POSITIVE LOGITS
    <bos>
    0.49
     devant
    0.47
    lección
    0.44
    elesai
    0.44
    发表于
    0.43
     coverage
    0.43
    Producción
    0.42
     filthy
    0.42
    Tôi
    0.42
     stuff
    0.42
    Activations Density 0.703%

    No Known Activations