© 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. 1194
    Prev
    Next
    INDEX
    Explanations

    the direction "East"

    oai_token-act-pair · gemini-2.0-flash

    East

    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
    RegressionTest
    -0.85
     Baillargeon
    -0.81
    TintMode
    -0.73
    '},
    -0.73
    Kaynakça
    -0.71
     arşivlendi
    -0.70
    "}")
    -0.69
    AsUp
    -0.69
     оригіналу
    -0.67
    Tikang
    -0.66
    POSITIVE LOGITS
    //
    0.49
     Crusade
    0.45
    Ore
    0.45
    clyde
    0.45
    bran
    0.42
    moor
    0.42
    right
    0.41
    Sim
    0.40
    field
    0.40
    pill
    0.40
    Activations Density 0.623%

    No Known Activations