© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10905
    Prev
    Next
    INDEX
    Explanations

    terms and names that are physics or math related

    oai_token-act-pair · gemini-2.0-flash

    Physics theory

    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
    lege
    -0.58
     particulières
    -0.55
    ArgsConstructor
    -0.53
     doctor
    -0.49
    })+
    -0.48
    wijl
    -0.47
     LoggerFactory
    -0.47
     galinha
    -0.47
     acuario
    -0.47
    rotnie
    -0.46
    POSITIVE LOGITS
     itſelf
    0.71
     myſelf
    0.65
     ProtoMessage
    0.65
     Jefus
    0.63
     greateſt
    0.63
    toMatchSnapshot
    0.63
     whoſe
    0.63
     Anſ
    0.62
     ſeveral
    0.62
    IntoConstraints
    0.61
    Activations Density 13.367%

    No Known Activations