© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15006
    Prev
    Next
    INDEX
    Explanations

    descriptions of explicit acts

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    SourceChecksum
    -0.51
    IndentedString
    -0.50
    protoimpl
    -0.48
    cyklopedia
    -0.47
    ığını
    -0.46
     بيها
    -0.46
    Personensuche
    -0.46
    oa̍t
    -0.46
    Jeografia
    -0.46
    SBATCH
    -0.44
    POSITIVE LOGITS
     inside
    0.90
     underneath
    0.82
     under
    0.81
     beneath
    0.76
     atop
    0.72
    原始内容存档于
    0.71
     amidst
    0.69
     INSIDE
    0.68
     unter
    0.68
     sotto
    0.66
    Activations Density 1.214%

    No Known Activations