© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5674
    Prev
    Next
    INDEX
    Explanations

    text related to statistics, percentages, and numbers

    oai_token-act-pair · gemini-2.0-flash

    special characters and technical terms

    np_token-act-pair-logits · gpt-4o-mini

    percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AddHtmlAttribute
    -0.49
     оригіналу
    -0.48
    awtextra
    -0.47
    Personensuche
    -0.47
    Semif
    -0.46
     konkrét
    -0.43
     bình
    -0.43
    βάλ
    -0.43
    podar
    -0.43
     enged
    -0.42
    POSITIVE LOGITS
     <=",
    0.64
    ]")]
    0.64
    ]--;
    0.60
     JpaRepository
    0.57
     المعيارى
    0.57
    ̍t
    0.56
     للمعارف
    0.56
    MigrationBuilder
    0.56
    NameInMap
    0.56
     nakalista
    0.55
    Activations Density 3.184%

    No Known Activations