© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7071
    Prev
    Next
    INDEX
    Explanations

    articles and research reports including related terms such as "a," "the," "report," and "study".

    oai_token-act-pair · gemini-2.0-flash

    terms related to studies and reports

    np_token-act-pair-logits · gpt-4o-mini

    studies and reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     negru
    -0.60
     gritos
    -0.59
     betrekking
    -0.57
     elettrico
    -0.56
     arbet
    -0.54
     rédaction
    -0.52
     stanga
    -0.52
    쟁
    -0.51
    vânt
    -0.51
     conosce
    -0.51
    POSITIVE LOGITS
     study
    1.43
     survey
    1.09
    study
    1.08
     report
    0.98
     Study
    0.92
    Study
    0.89
    survey
    0.87
    цездатний
    0.86
     STUDY
    0.86
    studie
    0.80
    Activations Density 2.153%

    No Known Activations