© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6681
    Prev
    Next
    INDEX
    Explanations

    Spanish words relating to chess championships

    oai_token-act-pair · gemini-2.0-flash

    Sports and world information

    np_max-act-logits · gemini-2.0-flash

    say "capitalized"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    enterOuterAlt
    -0.93
     ویکی‌پدیای
    -0.84
     مشين
    -0.82
    TestingModule
    -0.76
     MainAxisSize
    -0.73
     فريبيس
    -0.73
    GraphicsUnit
    -0.73
    ValueStyle
    -0.71
    存于互联网档案馆
    -0.70
    resave
    -0.68
    POSITIVE LOGITS
     Krim
    0.51
     Dinamarca
    0.48
    DateUtils
    0.47
    상
    0.46
    Tils
    0.46
     Suecia
    0.46
    ποι
    0.45
    mpotent
    0.45
    ific
    0.44
    FontOfSize
    0.44
    Activations Density 0.552%

    No Known Activations