© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9637
    Prev
    Next
    INDEX
    Explanations

    words or phrases in all caps, especially when they are part of headings, titles, or legal disclaimers.

    oai_token-act-pair · gemini-2.0-flash

    legal documents and web pages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    GEBURTSDATUM
    -1.06
     propOrder
    -0.88
    #+#
    -0.84
    MessageTagHelper
    -0.82
     незавершена
    -0.81
     getItemCount
    -0.80
    RegistryLite
    -0.79
    
    -0.79
     unknownFields
    -0.79
    <unused15>
    -0.79
    POSITIVE LOGITS
     собі
    0.25
     NDEBUG
    0.24
    f
    0.24
     TAMBÉM
    0.23
     maxn
    0.21
    lt
    0.21
    ÓW
    0.20
    l
    0.19
     RSITY
    0.19
     VERSITY
    0.19
    Activations Density 4.875%

    No Known Activations