© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13078
    Prev
    Next
    INDEX
    Explanations

    the word "it" and related pronouns within a short distance of words like "think" or "easy."

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.52
     it
    -1.37
    It
    -0.85
     It
    -0.73
    it
    -0.69
    它
    -0.58
     this
    -0.51
     the
    -0.50
    ↵
    -0.49
     and
    -0.46
    POSITIVE LOGITS
    herself
    0.89
    principalTable
    0.84
    ToBounds
    0.76
     DialogInterface
    0.73
    Yourself
    0.72
    yourself
    0.72
    DoubleQuotes
    0.71
     ddelweddau
    0.70
     Efq
    0.69
    entran
    0.69
    Activations Density 1.367%

    No Known Activations