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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11399
    Prev
    Next
    INDEX
    Explanations

    references to people and groups of people

    oai_token-act-pair · gemini-2.0-flash

    pronouns referring to people

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

    people

    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
    ########.
    -0.70
     itſelf
    -0.57
    Greet
    -0.57
    ÓS
    -0.55
    dbach
    -0.55
    acyjnych
    -0.54
    Ỡ
    -0.54
     الدولى
    -0.54
    новниш
    -0.54
    IVEREF
    -0.53
    POSITIVE LOGITS
     who
    2.08
    who
    1.42
     whom
    1.30
     quien
    1.23
     Who
    1.13
    Who
    1.06
     whose
    0.96
     quién
    0.96
    whom
    0.96
     quem
    0.90
    Activations Density 3.114%

    No Known Activations