© 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. 11930
    Prev
    Next
    INDEX
    Explanations

    words about concepts, problems, and high-level nouns.

    oai_token-act-pair · gemini-2.0-flash

    start or initial phase

    np_max-act · gemini-2.0-flash

    say "of" Method used: 2 — many following tokens are "of"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     "'");
    -0.67
     '.';
    -0.63
     '-';
    -0.57
     entanto
    -0.54
    odes
    -0.53
    ียม
    -0.52
     ".";
    -0.51
     '+':
    -0.51
    ließlich
    -0.51
    )';
    -0.49
    POSITIVE LOGITS
     تانيه
    0.83
     cherchés
    0.82
    GenerationType
    0.82
    ThroughAttribute
    0.79
    WebServlet
    0.79
    تقاوى
    0.79
     loosing
    0.78
    parsedMessage
    0.75
     disambiguazione
    0.74
     betweenstory
    0.73
    Activations Density 2.036%

    No Known Activations