© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    product descriptions, specifically focusing on bags, backpacks, and related hardware

    oai_token-act-pair · gemini-2.0-flash

    bags

    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
    setVerticalGroup
    -0.75
    adpleegd
    -0.73
    cipar
    -0.67
    NameInMap
    -0.62
    BeginContext
    -0.60
    الحياه
    -0.59
    RenderAtEndOf
    -0.59
    GEBURTSDATUM
    -0.58
     дописавши
    -0.58
     препратки
    -0.58
    POSITIVE LOGITS
    weih
    0.51
    epam
    0.49
     caixa
    0.48
    sheet
    0.47
     timedelta
    0.46
    baijan
    0.46
    FontOfSize
    0.46
    mmmmmm
    0.45
    っくり
    0.45
    фикации
    0.45
    Activations Density 4.543%

    No Known Activations