© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12334
    Prev
    Next
    INDEX
    Explanations

    words and phrases often found in technical documentation, especially those referring to other parts of the document

    oai_token-act-pair · gemini-2.0-flash

    reference

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    pattern
    -0.47
    المل
    -0.46
    bumptech
    -0.44
     Hand
    -0.44
    IsUnicode
    -0.43
     plane
    -0.42
     <<<<<<<<<<<<<<
    -0.42
    acer
    -0.42
     pat
    -0.41
     ext
    -0.41
    POSITIVE LOGITS
     reference
    1.50
    reference
    1.30
     Reference
    1.14
     recourse
    1.08
     REFERENCE
    1.03
    Reference
    1.02
     référence
    1.02
     referencia
    0.92
     referência
    0.91
    REFERENCE
    0.90
    Activations Density 4.868%

    No Known Activations