© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6720
    Prev
    Next
    INDEX
    Explanations

    words that refer to environmental conditions or industrial processes

    oai_token-act-pair · gemini-2.0-flash

    water and air quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    mack
    -0.52
    ABUL
    -0.51
    śmy
    -0.49
    ínű
    -0.49
    Pob
    -0.48
    juta
    -0.47
     Markup
    -0.47
    IVENESS
    -0.47
    tsz
    -0.46
     getApp
    -0.46
    POSITIVE LOGITS
    XmlAccessorType
    0.73
    المشاركات
    0.62
    Odour
    0.61
    setVerticalGroup
    0.59
     doInBackground
    0.59
    InitVars
    0.58
     GenerationType
    0.57
    verifyException
    0.57
    lgari
    0.56
    behälter
    0.55
    Activations Density 1.394%

    No Known Activations