© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12193
    Prev
    Next
    INDEX
    Explanations

    code snippets or sections with code-related terminology

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     photolibrary
    -1.16
     irq
    -1.10
     jira
    -1.08
     cmb
    -1.07
     ctl
    -1.05
     IRQ
    -1.04
     qc
    -1.04
     POI
    -1.04
     pii
    -1.03
    POI
    -1.03
    POSITIVE LOGITS
    ftagPool
    0.85
     szö
    0.72
    paisaje
    0.71
    zzle
    0.71
    <unused63>
    0.71
    robust
    0.71
      
    0.70
    팎
    0.70
    downtown
    0.68
    <unused61>
    0.68
    Activations Density 4.163%

    No Known Activations