© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12446
    Prev
    Next
    INDEX
    Explanations

    words or phrases that express personal opinions, preferences, or anecdotes, often in informal language

    oai_token-act-pair · gemini-2.0-flash

    my/mine

    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
     ويكيميديا
    -1.01
     photolibrary
    -1.00
    endphp
    -0.98
     Numerade
    -0.94
     surla
    -0.89
    featureID
    -0.88
     tartalomajánló
    -0.88
    endpush
    -0.87
     mouseY
    -0.84
    脚注の使い方
    -0.84
    POSITIVE LOGITS
     my
    0.73
     
    0.57
    my
    0.54
     all
    0.52
    :
    0.52
    i
    0.52
     a
    0.51
     two
    0.50
     (
    0.50
     i
    0.50
    Activations Density 1.687%

    No Known Activations