© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    words which come between or connect two things

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     O
    -0.38
     expression
    -0.37
     huy
    -0.36
     expr
    -0.35
    load
    -0.35
    lug
    -0.35
    <eos>
    -0.34
    ріш
    -0.34
    ski
    -0.34
     del
    -0.33
    POSITIVE LOGITS
     BorderRadius
    1.02
    AndEndTag
    0.98
     InputDecoration
    0.93
     мәкал
    0.91
     ExecuteAsync
    0.87
    Vidite
    0.82
    Билгалдахарш
    0.82
     ThemeData
    0.81
    исленность
    0.79
    IntoConstraints
    0.79
    Activations Density 3.108%

    No Known Activations