© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9195
    Prev
    Next
    INDEX
    Explanations

    pronouns such as "it", "she" and related words in different languages like "ela", "elle"

    oai_token-act-pair · gemini-2.0-flash

    Ela/elle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Савезне
    -1.05
     myſelf
    -0.83
    expandindo
    -0.81
    enterOuterAlt
    -0.73
     himſelf
    -0.71
    ]='\
    -0.71
     Monfieur
    -0.70
    FieldBuilder
    -0.69
    webElement
    -0.69
    poise
    -0.68
    POSITIVE LOGITS
     it
    0.69
     its
    0.57
     It
    0.48
    它們
    0.47
    它们
    0.46
    它们的
    0.46
    它
    0.46
    把它
    0.45
    It
    0.45
     their
    0.44
    Activations Density 1.520%

    No Known Activations