© 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. 5109
    Prev
    Next
    INDEX
    Explanations

    common programming keywords and characters, as well as some words indicating lists

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    WriteTagHelper
    -0.77
    RenderAtEndOf
    -0.73
     Мексичка
    -0.73
     Taktlose
    -0.70
     utafitiHapana
    -0.65
     فريبيس
    -0.62
     المعيارى
    -0.62
     Baillargeon
    -0.62
     Efq
    -0.61
     scolaires
    -0.60
    POSITIVE LOGITS
     Hit
    0.54
     Fight
    0.46
     Wish
    0.45
    Hozzáférés
    0.44
    steria
    0.42
     Hold
    0.42
     Hole
    0.41
     Run
    0.41
    тарь
    0.40
     Catch
    0.40
    Activations Density 1.267%

    No Known Activations