© 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. 334
    Prev
    Next
    INDEX
    Explanations

    dates, film-related terms, numbers and other metadata

    oai_token-act-pair · gemini-2.0-flash

    Arts and culture

    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
     nakalista
    -0.55
    TabIndex
    -0.54
    fony
    -0.48
    цездатний
    -0.46
    nvidia
    -0.45
    GeoNames
    -0.45
     مشين
    -0.45
     cliquez
    -0.44
    出版年
    -0.43
    ysz
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.65
     noastră
    0.60
    dstuk
    0.57
     propOrder
    0.56
     ProtoMessage
    0.55
    Rüyada
    0.55
    Geschiedenis
    0.54
    Personendaten
    0.54
    خرى
    0.54
    oa̍t
    0.54
    Activations Density 7.316%

    No Known Activations