© 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. 4073
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing popularity or commonality

    oai_token-act-pair · gemini-2.0-flash

    frequently used methodologies

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

    widely

    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
    SequentialGroup
    -0.69
     ModelExpression
    -0.68
     very
    -0.64
     kaarangay
    -0.61
    transQ
    -0.60
     NUKAT
    -0.60
    Datuak
    -0.59
     protoimpl
    -0.59
    QMetaType
    -0.58
    AccessorTable
    -0.57
    POSITIVE LOGITS
     discussed
    0.65
     used
    0.62
     sedia
    0.57
     studied
    0.57
     offered
    0.57
     commented
    0.54
     played
    0.52
     explored
    0.52
     held
    0.52
     mentioned
    0.52
    Activations Density 0.695%

    No Known Activations