© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5140
    Prev
    Next
    INDEX
    Explanations

    the base word "instruction" along with associated words

    oai_token-act-pair · gemini-2.0-flash

    instruction

    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
      
    -0.91
     
    -0.84
    ↵
    -0.82
    <i>
    -0.77
    P
    -0.76
     -
    -0.76
    A
    -0.76
    The
    -0.75
    R
    -0.69
    F
    -0.68
    POSITIVE LOGITS
    styleType
    1.17
    Personendaten
    1.09
     تضيفلها
    1.07
    IsContent
    1.05
    rungsseite
    1.05
    ValueStyle
    1.04
    saraba
    1.03
    SequentialGroup
    1.02
    GEBURTSDATUM
    1.02
    webElementXpaths
    1.00
    Activations Density 0.960%

    No Known Activations