© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10479
    Prev
    Next
    INDEX
    Explanations

    the definite article 'the' at the start of phrases and sentences

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     the
    -0.83
     a
    -0.75
     and
    -0.71
    .
    -0.67
     /
    -0.65
    ,
    -0.63
     
    -0.60
     (
    -0.57
     an
    -0.56
    ↵↵
    -0.55
    POSITIVE LOGITS
     myſelf
    1.67
     itſelf
    1.63
     Efq
    1.56
     pleaſure
    1.55
     Majefty
    1.53
     purpoſe
    1.51
    ſelf
    1.48
     Jefus
    1.47
     themſelves
    1.47
     ſind
    1.46
    Activations Density 4.782%

    No Known Activations