© 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. 11483
    Prev
    Next
    INDEX
    Explanations

    common words such as "the" and "new"

    oai_token-act-pair · gemini-2.0-flash

    the/a

    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
    ^(@)
    -0.63
    RuleContext
    -0.59
     msglen
    -0.57
    AccessFile
    -0.54
    hyrchwyd
    -0.54
    ynos
    -0.54
     raiſ
    -0.54
     ogóle
    -0.53
    jsonwebtoken
    -0.53
     AssemblyCulture
    -0.53
    POSITIVE LOGITS
     new
    3.31
    new
    2.80
     neuen
    2.14
     nueva
    2.14
     nuevos
    2.11
     nieuwe
    2.09
     neue
    2.08
     nuevas
    2.06
     nuevo
    2.05
    新的
    2.02
    Activations Density 2.114%

    No Known Activations