© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4041
    Prev
    Next
    INDEX
    Explanations

    text excerpts from business and news publications with logos, dates, and article summaries

    oai_token-act-pair · gemini-2.0-flash

    non-English words or foreign terms

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

    Foreign words

    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
    rungsseite
    -0.61
    )++;
    -0.60
    principalTable
    -0.59
    fjspx
    -0.56
    Tikang
    -0.54
    moiselle
    -0.52
    "]));
    -0.50
    Datuak
    -0.50
    //});
    -0.49
    //}
    -0.48
    POSITIVE LOGITS
     sulphide
    0.58
     milioane
    0.57
     vuoden
    0.56
     winters
    0.54
     femei
    0.53
     îna
    0.52
    ›
    0.52
     fevereiro
    0.52
     jardim
    0.51
     februarie
    0.51
    Activations Density 7.080%

    No Known Activations