© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8564
    Prev
    Next
    INDEX
    Explanations

    the prefix "pen" and the substring "men", while also activating for some words in a different language

    oai_token-act-pair · gemini-2.0-flash

    Locations/names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TypedDataSet
    -0.54
    #
    -0.49
    __(/*!
    -0.46
    ooga
    -0.45
     s
    -0.44
    :✨
    -0.43
     nakalista
    -0.41
    eslint
    -0.41
    romyalgia
    -0.41
    bindingNavigator
    -0.41
    POSITIVE LOGITS
    unjukan
    0.76
    ampung
    0.75
    jangkau
    0.75
    unggu
    0.67
    ampilkan
    0.66
    unjang
    0.66
     StatelessWidget
    0.65
    ampilan
    0.63
    unjukkan
    0.60
    awaran
    0.60
    Activations Density 0.685%

    No Known Activations