© 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. 4457
    Prev
    Next
    INDEX
    Explanations

    capitalized words or proper nouns in the middle of sentences

    oai_token-act-pair · gemini-2.0-flash

    Code/Software

    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
     (
    -0.50
      
    -0.49
     and
    -0.47
    lu
    -0.46
    ,
    -0.45
        
    -0.44
    Chat
    -0.39
    g
    -0.39
    mo
    -0.38
     blancas
    -0.38
    POSITIVE LOGITS
     ddelweddau
    1.18
    Personensuche
    1.13
    featureID
    1.04
    IUrlHelper
    0.98
     дописавши
    0.96
     تضيفلها
    0.95
     bezeichneter
    0.94
    providedIn
    0.94
     Signalez
    0.93
    XmlAccessType
    0.92
    Activations Density 3.040%

    No Known Activations