© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8713
    Prev
    Next
    INDEX
    Explanations

    the phrase "that's" or "that is" followed by an adjective or noun

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     femenina
    -0.57
    Життєпис
    -0.57
    HtmlAttribute
    -0.56
     ovp
    -0.56
     metálica
    -0.56
     sarili
    -0.54
     mandible
    -0.51
     barbati
    -0.51
     femei
    -0.50
     adenocarcinoma
    -0.50
    POSITIVE LOGITS
    addPreferredGap
    0.63
     EdgeInsets
    0.61
    Hozzáférés
    0.59
    IVEREF
    0.59
    evos
    0.57
     uns
    0.57
    ✨:
    0.56
    WebServlet
    0.55
     positive
    0.54
    savefig
    0.53
    Activations Density 0.561%

    No Known Activations