© 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. 6700
    Prev
    Next
    INDEX
    Explanations

    helping or finding a solution to a problem.

    oai_token-act-pair · gemini-2.0-flash

    pronouns referring to people

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

    "they"

    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
    DllImport
    -0.44
    }>{
    -0.44
    "><?
    -0.43
     it
    -0.42
    cupertino
    -0.41
     swoich
    -0.38
     svých
    -0.38
    esanan
    -0.36
     свои
    -0.35
    koda
    -0.35
    POSITIVE LOGITS
     they
    3.19
     They
    2.98
    They
    2.95
     them
    2.92
    they
    2.73
     mereka
    2.59
    他们
    2.44
     họ
    2.38
     Mereka
    2.36
     ihnen
    2.33
    Activations Density 13.803%

    No Known Activations