© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    topics related to the discovery of the Americas

    oai_token-act-pair · gemini-2.0-flash

    explorers and exploration

    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
    findpost
    -0.53
    一面
    -0.47
     glatt
    -0.45
    ButterKnife
    -0.45
    rement
    -0.43
    localctx
    -0.42
    pais
    -0.42
     owner
    -0.42
    mut
    -0.41
    خصة
    -0.41
    POSITIVE LOGITS
     Theſe
    0.72
     Efq
    0.71
     quæ
    0.70
     '\\;'
    0.69
    GraphicsUnit
    0.69
    Organisateur
    0.67
     Majefty
    0.67
     Beſ
    0.66
    SBATCH
    0.63
     Monfieur
    0.63
    Activations Density 1.252%

    No Known Activations