© 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. 1329
    Prev
    Next
    INDEX
    Explanations

    words and phrases involved in performing studies and experiments.

    oai_token-act-pair · gemini-2.0-flash

    programming tasks

    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
     task
    -2.84
     Task
    -2.72
    task
    -2.69
    Task
    -2.69
     TASK
    -2.52
     Tasks
    -2.47
     tasks
    -2.44
    TASK
    -2.38
    tasks
    -2.27
    Tasks
    -2.20
    POSITIVE LOGITS
    Lähteet
    0.56
    httphttps
    0.51
    ModelAdmin
    0.46
    vage
    0.41
     surla
    0.41
     nucleation
    0.40
     ویکی‌پدیای
    0.39
    vad
    0.39
    masan
    0.39
    Hozzáférés
    0.38
    Activations Density 1.402%

    No Known Activations