© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7406
    Prev
    Next
    INDEX
    Explanations

    the word "target" and words associated with marketing and goals.

    oai_token-act-pair · gemini-2.0-flash

    tokens indicating targeting or audience selection

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

    target

    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
     wireType
    -0.85
    ThroughAttribute
    -0.78
    ValueStyle
    -0.72
    Искәрмәләр
    -0.64
     يتيمه
    -0.63
     brancas
    -0.60
     estimés
    -0.58
    principalColumn
    -0.57
    ReusableCell
    -0.57
     चीज़ों
    -0.57
    POSITIVE LOGITS
    endregion
    0.57
    dbo
    0.49
     Dobson
    0.43
    ced
    0.42
     Biochim
    0.42
    indd
    0.42
    ร์
    0.41
     Frid
    0.41
    っぽ
    0.41
     عوض
    0.41
    Activations Density 8.119%

    No Known Activations