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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10535
    Prev
    Next
    INDEX
    Explanations

    the word "Chex" or similar variants, which could be usernames or references in a chat log context

    oai_token-act-pair · gemini-2.0-flash

    Che

    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
    omitempty
    -0.84
    findpost
    -0.71
     defaultstate
    -0.62
     للمعارف
    -0.62
    contentLoaded
    -0.61
     AssemblyCompany
    -0.61
    SourceChecksum
    -0.61
    EDEFAULT
    -0.61
     Italijanski
    -0.60
     nonatomic
    -0.58
    POSITIVE LOGITS
     lenker
    0.44
    teries
    0.44
    таратура
    0.42
    ագրություններ
    0.41
    sire
    0.41
     Bung
    0.40
    ebus
    0.39
     ActivatedRoute
    0.39
    retanto
    0.39
    הערות
    0.38
    Activations Density 0.285%

    No Known Activations