© 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. 5736
    Prev
    Next
    INDEX
    Explanations

    words related to storytelling, including genres, plot elements, and descriptions of reader experience.

    oai_token-act-pair · gemini-2.0-flash

    technical terms

    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
     jsPsych
    -0.73
     EconPapers
    -0.61
     referrerpolicy
    -0.61
    WriteBarrier
    -0.60
     {},
    -0.59
    jspx
    -0.56
    -),
    -0.56
     (),
    -0.56
    ),
    -0.54
    *),
    -0.54
    POSITIVE LOGITS
    ManagedBean
    0.54
    .
    0.54
    closePath
    0.50
    ंदीखरीदारी
    0.48
    。
    0.46
     Lightboxes
    0.44
     AssemblyVersion
    0.44
     fere
    0.43
    IUrlHelper
    0.43
     aisladas
    0.42
    Activations Density 22.287%

    No Known Activations