© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6734
    Prev
    Next
    INDEX
    Explanations

    text from scientific papers involving equations and numerical simulations

    oai_token-act-pair · gemini-2.0-flash

    step and increment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     defaultstate
    -0.69
    uance
    -0.56
    WireFormat
    -0.56
     >=",
    -0.56
    Portail
    -0.54
     useAuth
    -0.53
    PointerException
    -0.52
     noqa
    -0.52
     propTypes
    -0.52
    erdings
    -0.51
    POSITIVE LOGITS
     step
    0.98
    step
    0.84
     Step
    0.81
     increments
    0.79
     increment
    0.79
     steps
    0.79
    Step
    0.77
     grid
    0.76
     resolution
    0.75
     discretization
    0.74
    Activations Density 3.358%

    No Known Activations