© 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. 4440
    Prev
    Next
    INDEX
    Explanations

    dialogue or questions and answers

    oai_token-act-pair · gemini-2.0-flash

    Expressing understanding

    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
     typelib
    -0.72
    RenderAtEndOf
    -0.70
     bayonet
    -0.65
    richTextPanel
    -0.63
    multer
    -0.62
     AppBundle
    -0.61
     bridegroom
    -0.61
     shipwreck
    -0.61
    Portály
    -0.60
     Cæsar
    -0.60
    POSITIVE LOGITS
     understood
    1.24
     okay
    1.15
     ok
    1.13
     understand
    1.13
     understanding
    1.12
     OK
    1.08
    understood
    1.05
    Understood
    1.04
     Understanding
    1.02
    understand
    1.02
    Activations Density 1.038%

    No Known Activations