© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8502
    Prev
    Next
    INDEX
    Explanations

    words related to programming, medicine, and quitting smoking

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     myſelf
    -0.64
     دیکھیے
    -0.58
     CreateTagHelper
    -0.50
     mace
    -0.49
    Autoritní
    -0.49
     yourselves
    -0.49
    pexpr
    -0.49
     scones
    -0.48
    Попис
    -0.48
    elemField
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    0.71
     gangen
    0.55
    crity
    0.54
     British
    0.53
    British
    0.53
    execSQL
    0.52
    bereit
    0.51
     artikkelen
    0.50
     الاطلاع
    0.50
    ynı
    0.48
    Activations Density 1.286%

    No Known Activations