© 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. 7840
    Prev
    Next
    INDEX
    Explanations

    descriptive language for perfumes and scents

    oai_token-act-pair · gemini-2.0-flash

    technical or coding elements

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

    Code/foreign language

    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
    niosek
    -0.56
     tett
    -0.54
    OutputPath
    -0.50
    issex
    -0.49
    SizeMode
    -0.49
    ฐาน
    -0.46
    Adapter
    -0.43
    ListAdapter
    -0.43
     reflexão
    -0.42
    IVOS
    -0.42
    POSITIVE LOGITS
    abestanden
    0.78
    BeginContext
    0.71
     }</
    0.68
     كومونز
    0.64
    SBATCH
    0.63
    +");
    0.61
     مرئيه
    0.60
     المعيارى
    0.60
     protoimpl
    0.59
    getKeyCode
    0.59
    Activations Density 1.453%

    No Known Activations