© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    the prefix "ex"

    oai_token-act-pair · gemini-2.0-flash

    ex

    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
    SequentialGroup
    -0.63
     Autorizaciones
    -0.61
    PerformLayout
    -0.59
    mphony
    -0.57
    ISupport
    -0.57
    Становништво
    -0.55
     arşivlendi
    -0.53
    stateMutability
    -0.53
    Parcelize
    -0.53
    جستارهای
    -0.52
    POSITIVE LOGITS
    Personendaten
    0.66
    rawDesc
    0.46
     Wikimedijinoj
    0.46
     flesta
    0.45
     Савезне
    0.43
     ögon
    0.43
    itets
    0.42
    out
    0.41
     arbete
    0.40
     jäsen
    0.40
    Activations Density 0.414%

    No Known Activations