© 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. 12123
    Prev
    Next
    INDEX
    Explanations

    the pronoun 'I' and related words (me, my)

    oai_token-act-pair · gemini-2.0-flash

    posts and threads

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

    posting threads

    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
    DockStyle
    -0.74
    SceneManagement
    -0.60
    rrggbb
    -0.60
    อนไลน์
    -0.59
    aarrggbb
    -0.58
     Процитовано
    -0.58
    ParallelGroup
    -0.58
    IBOutlet
    -0.57
    WebServlet
    -0.55
     WaitForSeconds
    -0.55
    POSITIVE LOGITS
     post
    2.14
     posts
    2.13
     thread
    2.05
     posting
    1.81
    post
    1.74
     threads
    1.73
     Posts
    1.66
     Post
    1.65
     posted
    1.63
     Thread
    1.63
    Activations Density 3.796%

    No Known Activations