© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11849
    Prev
    Next
    INDEX
    Explanations

    the word "of" and phrases "all of the"

    oai_token-act-pair · gemini-2.0-flash

    Middles of phrases

    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
     yet
    -1.55
    yet
    -1.42
    Yet
    -1.30
     Yet
    -1.27
     YET
    -1.23
     ever
    -0.86
     Ever
    -0.71
    ever
    -0.71
    Ever
    -0.67
     محفوظة
    -0.67
    POSITIVE LOGITS
    protoimpl
    0.59
    OTHY
    0.56
     Existence
    0.55
     existence
    0.54
     any
    0.52
     existência
    0.52
     existencia
    0.51
    ázquez
    0.51
    closedir
    0.50
     StringTokenizer
    0.50
    Activations Density 1.132%

    No Known Activations