© 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. 5264
    Prev
    Next
    INDEX
    Explanations

    computer code like syntax

    oai_token-act-pair · gemini-2.0-flash

    camera/scene

    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
     dealership
    -0.66
    VENTORY
    -0.63
     فريبيس
    -0.58
    SequentialGroup
    -0.57
     ProtoMessage
    -0.55
    EndContext
    -0.55
     resourceCulture
    -0.54
     Doreen
    -0.52
     Inventory
    -0.52
     surla
    -0.52
    POSITIVE LOGITS
     camera
    0.62
    навли
    0.56
    帖最后由
    0.54
     box
    0.51
    camera
    0.51
     Camera
    0.51
    ########.
    0.51
    Camera
    0.49
     scene
    0.49
    клопе
    0.48
    Activations Density 0.536%

    No Known Activations