© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    titles, initials, and honorifics for people

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
    ^(@)
    -1.25
     Forumite
    -1.17
     itſelf
    -1.15
     $_"
    -1.13
     myſelf
    -1.12
    ſelves
    -1.09
     themſelves
    -1.09
    ſelf
    -1.07
     Majefty
    -1.07
    olesale
    -1.05
    POSITIVE LOGITS
     revés
    0.50
     corrientes
    0.47
     abusos
    0.46
     pertes
    0.45
     cristales
    0.45
     rayures
    0.44
     nuages
    0.43
     terrenos
    0.42
     urbanas
    0.42
     commerciales
    0.41
    Activations Density 4.555%

    No Known Activations