© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11057
    Prev
    Next
    INDEX
    Explanations

    technical mathematical and scientific jargon

    oai_token-act-pair · gemini-2.0-flash

    Development/application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     tartalomajánló
    -1.22
     itſelf
    -1.14
     pleaſure
    -1.12
    出版年
    -1.12
     Jefus
    -1.11
     myſelf
    -1.09
     Majefty
    -1.08
     Diſ
    -1.08
     iſt
    -1.06
     ſche
    -1.05
    POSITIVE LOGITS
     
    0.51
    ↵↵
    0.49
     re
    0.48
     in
    0.46
    ↵
    0.45
    ...
    0.44
    <eos>
    0.43
    n
    0.42
     Do
    0.42
     (
    0.41
    Activations Density 35.131%

    No Known Activations