© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5215
    Prev
    Next
    INDEX
    Explanations

    many of the word 'in'

    oai_token-act-pair · gemini-2.0-flash

    gerunds and present participles

    np_token-act-pair-logits · gpt-4o-mini

    In

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     متعلقه
    -0.88
    ंदीखरीदारी
    -0.82
    󠁢
    -0.80
    GraphicsUnit
    -0.80
    httphttps
    -0.78
     Vikipedi
    -0.74
    ngths
    -0.71
    躇
    -0.70
     noDo
    -0.69
     виправивши
    -0.68
    POSITIVE LOGITS
     so
    0.56
     seeking
    0.49
     giving
    0.46
     emphasizing
    0.45
     performing
    0.45
     stressing
    0.44
     creating
    0.44
     suggesting
    0.43
     outlining
    0.42
     attempting
    0.42
    Activations Density 0.987%

    No Known Activations