© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12790
    Prev
    Next
    INDEX
    Explanations

    technical or industrial language

    oai_token-act-pair · gemini-2.0-flash

    Technical and automated processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -0.72
     nahilalakip
    -0.53
     forcément
    -0.50
    heureusement
    -0.46
     Namely
    -0.43
    最快更新
    -0.42
     notare
    -0.41
    斥
    -0.41
    :✨
    -0.41
     okuyayım
    -0.41
    POSITIVE LOGITS
    MarshalTo
    0.65
    yntaxException
    0.60
    DrawerToggle
    0.58
    IndentedString
    0.55
    fclose
    0.55
     Qua
    0.55
    SceneManagement
    0.55
     purchase
    0.54
     cref
    0.54
    NewUrlParser
    0.53
    Activations Density 3.390%

    No Known Activations