© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14903
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people, places, and organizations

    oai_token-act-pair · gemini-2.0-flash

    Words describing communication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    InputBorder
    -0.56
     économies
    -0.48
    ]")]
    -0.47
     vzh
    -0.46
     lenker
    -0.45
    ContentAsync
    -0.42
     {*}
    -0.41
    BeginInit
    -0.41
     '-';
    -0.41
     '.';
    -0.39
    POSITIVE LOGITS
     told
    1.38
     announced
    1.30
     introduced
    1.30
     argued
    1.29
     asked
    1.27
     explained
    1.26
     said
    1.24
     thanked
    1.24
     gave
    1.23
     revealed
    1.22
    Activations Density 4.001%

    No Known Activations