© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12936
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest a cost or requirement

    oai_token-act-pair · gemini-2.0-flash

    expense or cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     surla
    -0.74
     Bort
    -0.60
    databinding
    -0.55
    |}{}
    -0.52
    InputBorder
    -0.52
    chism
    -0.51
     bander
    -0.51
    >());
    -0.50
    ("]");
    -0.49
     intptr
    -0.49
    POSITIVE LOGITS
    NameInMap
    0.71
     estimés
    0.65
    cần
    0.59
     وتسجيلات
    0.54
     professionali
    0.54
     jätte
    0.54
     ocup
    0.52
     membutuhkan
    0.52
     memerlukan
    0.51
     belast
    0.51
    Activations Density 0.592%

    No Known Activations