© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8054
    Prev
    Next
    INDEX
    Explanations

    code related to URLs and accessing resources, especially on Github and Deno

    oai_token-act-pair · gemini-2.0-flash

    GitHub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    kháu
    -0.59
    Aholisi
    -0.53
    ForValue
    -0.53
    himovic
    -0.53
    IndentedString
    -0.52
    новништво
    -0.51
    monary
    -0.51
    いわ
    -0.50
    rophobic
    -0.50
    idex
    -0.50
    POSITIVE LOGITS
    bukkit
    0.77
    Xna
    0.58
    UserScript
    0.57
    PRNewswire
    0.57
     }),
    0.56
     Exacts
    0.55
    politico
    0.55
    ())),
    0.54
     ReSharper
    0.54
     initWithFrame
    0.54
    Activations Density 1.566%

    No Known Activations