© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11446
    Prev
    Next
    INDEX
    Explanations

    words with the prefixes "im-", "in-", "re-", "ad-", or "inter-", often related to actions or states.

    oai_token-act-pair · gemini-2.0-flash

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    PerformLayout
    -0.89
    adecimal
    -0.81
    脚注の使い方
    -0.77
     nakalista
    -0.77
    visiae
    -0.74
    utilisons
    -0.74
    sterious
    -0.74
    twimg
    -0.73
    IMPORTED
    -0.71
    ksikon
    -0.71
    POSITIVE LOGITS
     tredje
    0.43
     اینکه
    0.39
    reuung
    0.38
     perdagangan
    0.38
    nivel
    0.38
     LIABLE
    0.37
    NewUrlParser
    0.36
     ότι
    0.36
    庁
    0.36
     Ly
    0.36
    Activations Density 2.950%

    No Known Activations