© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15776
    Prev
    Next
    INDEX
    Explanations

    date formatting code

    oai_token-act-pair · gemini-2.0-flash

    Date formats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Rhestr
    -0.74
    IUrlHelper
    -0.65
    errHandler
    -0.63
     يتيمه
    -0.60
    Gweler
    -0.59
    rungsseite
    -0.58
    principalTable
    -0.57
     Alfaro
    -0.56
    Aktualisiert
    -0.55
    ophora
    -0.55
    POSITIVE LOGITS
    endphp
    0.59
     pán
    0.50
     greateſt
    0.49
     preſent
    0.45
     CDT
    0.45
     kanker
    0.44
    glieder
    0.43
     pleaſure
    0.42
     Least
    0.42
     seid
    0.42
    Activations Density 1.210%

    No Known Activations