© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13862
    Prev
    Next
    INDEX
    Explanations

    the word 'and' or conjunctions

    oai_token-act-pair · gemini-2.0-flash

    pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ourselves
    -0.67
     myself
    -0.46
    myself
    -0.44
    раздо
    -0.44
    likopter
    -0.44
    емся
    -0.43
    IsRequired
    -0.43
     нами
    -0.42
    ıyoruz
    -0.42
     próprias
    -0.40
    POSITIVE LOGITS
     he
    1.23
     she
    1.15
     they
    1.15
     он
    1.02
     она
    1.02
     они
    0.95
     він
    0.94
     वह
    0.93
     вона
    0.91
     вони
    0.88
    Activations Density 3.663%

    No Known Activations