© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10971
    Prev
    Next
    INDEX
    Explanations

    times in the morning or afternoon using "a.m." and "p.m."

    oai_token-act-pair · gemini-2.0-flash

    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
     AssemblyCulture
    -1.11
     purpoſe
    -1.02
     ſche
    -0.97
     pleaſure
    -0.87
     Majefty
    -0.87
     betweenstory
    -0.85
     Jefus
    -0.85
    seamnă
    -0.84
     juſt
    -0.84
     myſelf
    -0.83
    POSITIVE LOGITS
     hole
    0.46
     ca
    0.43
     trong
    0.41
     You
    0.41
    hl
    0.40
     ma
    0.40
    cartItem
    0.39
     de
    0.39
     l
    0.39
    CJK
    0.39
    Activations Density 0.649%

    No Known Activations