© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2100
    Prev
    Next
    INDEX
    Explanations

    content related to news articles and press releases

    oai_token-act-pair · gemini-2.0-flash

    news snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    WarningLevel
    -0.69
    StoryboardSegue
    -0.67
    SharedDtor
    -0.66
     للاسماء
    -0.65
    +#+
    -0.64
    sizeCache
    -0.64
     المعيارى
    -0.62
    +#+#
    -0.61
     صوتيه
    -0.60
    ftagPool
    -0.60
    POSITIVE LOGITS
    ASTIC
    0.51
    теристика
    0.49
    easeOut
    0.48
    operating
    0.48
    cytic
    0.47
     dry
    0.46
    Izvori
    0.45
    chanan
    0.45
    Mga
    0.44
     Simply
    0.44
    Activations Density 0.805%

    No Known Activations