© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15909
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, HTML artifacts, and tokens associated with coding and business

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ujednoznacz
    -0.56
     accompanying
    -0.54
     cru
    -0.54
    Newswire
    -0.53
     يتيمه
    -0.53
     id
    -0.52
     vig
    -0.50
    +:+
    -0.50
     hy
    -0.50
     associated
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.62
     femininas
    0.60
     ricerche
    0.59
     betweenstory
    0.57
     douleurs
    0.57
     henkil
    0.57
     américains
    0.57
     utveckling
    0.56
    Kubernetes
    0.56
     verksamhet
    0.56
    Activations Density 4.662%

    No Known Activations