© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4014
    Prev
    Next
    INDEX
    Explanations

    fragments of the word "circumstance" along with seemingly random capitalized letters and prefixes "under" "che" "hur" and "hon"

    oai_token-act-pair · gemini-2.0-flash

    say "st" words

    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
     وصلة
    -0.47
    nextDouble
    -0.44
    lccn
    -0.43
    ">//
    -0.43
    RDONLY
    -0.43
    beza
    -0.42
    setVerticalGroup
    -0.42
     đóng
    -0.42
    COLE
    -0.42
    almaz
    -0.41
    POSITIVE LOGITS
    St
    0.84
     ST
    0.84
     st
    0.82
     stan
    0.81
    stm
    0.80
    STK
    0.79
    STP
    0.79
     Ster
    0.78
    ST
    0.77
    STC
    0.77
    Activations Density 1.761%

    No Known Activations