© 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. 6180
    Prev
    Next
    INDEX
    Explanations

    language related to warranties and guarantees with possible connection to dates, price and brands

    oai_token-act-pair · gemini-2.0-flash

    technical terms or components in software development

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

    Warranty information

    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
     Normdatei
    -0.77
    Geplaatst
    -0.76
     חיצוניים
    -0.75
    oredCriteria
    -0.74
    HomeAsUpEnabled
    -0.71
     متعلقه
    -0.71
    IsContent
    -0.68
    StoreMessageInfo
    -0.63
     Offisielt
    -0.62
    données
    -0.60
    POSITIVE LOGITS
    scalatest
    0.52
     useRef
    0.50
     jadx
    0.46
     Belgische
    0.43
    ViewChild
    0.42
     JADX
    0.42
     parts
    0.41
     lẻ
    0.41
    힣
    0.41
     Perr
    0.40
    Activations Density 0.795%

    No Known Activations