© 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. 11328
    Prev
    Next
    INDEX
    Explanations

    words related to disease and micro-organisms

    oai_token-act-pair · gemini-2.0-flash

    terms related to microorganisms

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

    microorganisms

    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
    umenical
    -0.50
    كذا
    -0.48
    principalColumn
    -0.48
     OkHttpClient
    -0.46
    vádz
    -0.45
     जिसमें
    -0.45
     تانيه
    -0.45
    deauna
    -0.45
    )}</
    -0.44
    ḷ
    -0.44
    POSITIVE LOGITS
    IndentedString
    0.67
    windowFixed
    0.65
     CreateTagHelper
    0.61
     defaultstate
    0.59
    Хьажоргаш
    0.57
     resourceCulture
    0.57
    prefixer
    0.55
     microorganisms
    0.52
    WriteBarrier
    0.51
     microbes
    0.51
    Activations Density 4.697%

    No Known Activations