© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6441
    Prev
    Next
    INDEX
    Explanations

    words related to ownership ("your" is very common) and potentially branding.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns and related terms

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

    your

    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
     your
    -1.17
    your
    -1.09
    Your
    -1.02
    AndEndTag
    -0.98
     youre
    -0.92
     yourself
    -0.89
     yourselves
    -0.84
     Your
    -0.84
    ของคุณ
    -0.82
    YOUR
    -0.80
    POSITIVE LOGITS
     end
    0.56
    queryInterface
    0.52
     favorite
    0.51
    TypedDataSet
    0.49
     terminal
    0.49
     ideal
    0.49
    ulam
    0.48
     goal
    0.48
     ch
    0.48
     particular
    0.48
    Activations Density 2.569%

    No Known Activations