© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 503
    Prev
    Next
    INDEX
    Explanations

    words related to product support and product features

    oai_token-act-pair · gemini-2.0-flash

    product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     "..\..\
    -0.58
     désigne
    -0.54
    IZONT
    -0.53
    icillin
    -0.53
    ليج
    -0.51
     Bader
    -0.50
     bonté
    -0.49
    ONSORED
    -0.49
     kepad
    -0.49
    itonitis
    -0.49
    POSITIVE LOGITS
     typelib
    0.57
    titleMargin
    0.54
     يتيمه
    0.51
    EndGlobalSection
    0.50
    Manbalar
    0.50
    варь
    0.50
    ագրություններ
    0.49
    nith
    0.49
     Host
    0.48
     TRES
    0.47
    Activations Density 0.776%

    No Known Activations