© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    the word "old" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    old

    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
    ш
    -0.43
     in
    -0.40
     Tisch
    -0.38
     meren
    -0.38
    Change
    -0.38
    nextLine
    -0.38
    den
    -0.38
    ppel
    -0.37
     Change
    -0.37
    kon
    -0.36
    POSITIVE LOGITS
     Normdatei
    1.13
    parsedMessage
    1.03
     indisponible
    0.87
    Демографія
    0.87
     Baillargeon
    0.84
     propOrder
    0.84
    tvguidetime
    0.83
    featureID
    0.83
     EconPapers
    0.82
     @"/
    0.82
    Activations Density 1.948%

    No Known Activations