© 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. 10361
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mall" and specific malls

    oai_token-act-pair · gemini-2.0-flash

    snippets of text

    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
    DispatchToProps
    -0.76
    Autoritní
    -0.66
     VIAF
    -0.61
    AccessorTable
    -0.61
     lenker
    -0.60
     EdgeInsets
    -0.60
    QMetaType
    -0.59
    WithIOException
    -0.58
     незавершена
    -0.58
     onAnimation
    -0.58
    POSITIVE LOGITS
    ImageContext
    0.53
    ++);
    0.51
    JspWriter
    0.47
    mak
    0.46
     mak
    0.46
     tul
    0.42
    RTRS
    0.42
    意思
    0.41
    ++];
    0.41
    utilisons
    0.41
    Activations Density 0.368%

    No Known Activations