© 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. 6158
    Prev
    Next
    INDEX
    Explanations

    descriptions of various products, including electronics, home goods and clothing.

    oai_token-act-pair · gemini-2.0-flash

    words relating to connectors or conjunctions

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

    product descriptions

    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
     habet
    -0.61
    queryInterface
    -0.52
     indépend
    -0.50
     géneros
    -0.49
    DataAnnotations
    -0.49
    OutputType
    -0.48
    protoimpl
    -0.48
     DataTypes
    -0.46
    MigrationBuilder
    -0.45
    Subview
    -0.45
    POSITIVE LOGITS
     with
    0.71
    Diweddarwch
    0.60
     với
    0.54
    ]]
    0.54
     avec
    0.53
    עם
    0.51
    cipitation
    0.51
     dengan
    0.51
    セット
    0.50
     sleeves
    0.50
    Activations Density 3.916%

    No Known Activations