© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    mentions of "I" and/or "you", often in the context of something never having been done before

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'never'

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

    never

    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
    expandindo
    -0.67
     CURIAM
    -0.56
    دانشنامهٔ
    -0.51
    orianCalendar
    -0.50
     endregion
    -0.49
    MockBean
    -0.47
     متعلقه
    -0.47
     cref
    -0.46
    bootstrapcdn
    -0.46
    WebServlet
    -0.46
    POSITIVE LOGITS
     never
    2.86
    never
    2.56
     Never
    2.48
    Never
    2.41
     NEVER
    2.08
     nunca
    1.98
    NEVER
    1.98
     nigdy
    1.85
     Nunca
    1.80
     aldrig
    1.80
    Activations Density 1.670%

    No Known Activations