© 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. 4214
    Prev
    Next
    INDEX
    Explanations

    tokens within code blocks, place names in Poland, palaeontology terminology, legal jargon, and words relating to obstetric medicine

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    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
    mları
    -0.68
     adresu
    -0.64
    ıları
    -0.61
    uzu
    -0.59
    leri
    -0.59
    évaluateur
    -0.57
    ları
    -0.57
     كومونز
    -0.56
    seli
    -0.55
    aları
    -0.54
    POSITIVE LOGITS
    Географиясе
    0.70
    StructEnd
    0.59
    WebMethod
    0.58
     FetchType
    0.58
    ğını
    0.54
    complexContent
    0.54
     baterie
    0.54
    WebElement
    0.53
     dobr
    0.50
    TagMode
    0.50
    Activations Density 2.423%

    No Known Activations