© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15480
    Prev
    Next
    INDEX
    Explanations

    scientific writing where results, ideas, or methods are approached through questions, descriptions, and analysis and are presented in a deliberate structured manner.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     дописавши
    -0.73
    verwijspagina
    -0.57
     архивлан
    -0.54
     &___
    -0.52
    Hochspringen
    -0.52
    Pyx
    -0.50
    FormTagHelper
    -0.49
    setopt
    -0.48
     виправивши
    -0.47
    Jîn
    -0.47
    POSITIVE LOGITS
     OMITBAD
    0.71
    ónimos
    0.61
     doInBackground
    0.59
    hyrchwyd
    0.59
     Forsyth
    0.58
     metropolitana
    0.56
    Kontra
    0.55
     TAMBÉM
    0.54
     enemy
    0.53
     문서
    0.52
    Activations Density 6.723%

    No Known Activations