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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 843
    Prev
    Next
    INDEX
    Explanations

    the word sequences "a committee to", "the [word] of", "[country]'s [word]" and the word "Bourita"

    oai_token-act-pair · gemini-2.0-flash

    Middle Eastern politics

    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
    ContentAsync
    -0.74
    NameInMap
    -0.62
    脚注の使い方
    -0.60
     nakalista
    -0.57
    UnusedPrivate
    -0.57
     Вікі
    -0.57
    marginHorizontal
    -0.56
    Jeografia
    -0.56
    Manbalar
    -0.55
    AddTagHelper
    -0.55
    POSITIVE LOGITS
     GenerationType
    0.49
    िता
    0.46
    Popular
    0.45
    GraphicsUnit
    0.45
    årige
    0.44
    qid
    0.44
    ![
    0.43
     qued
    0.43
    InsertCommand
    0.41
    FileDialog
    0.41
    Activations Density 1.277%

    No Known Activations