© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12805
    Prev
    Next
    INDEX
    Explanations

    bulleted lists, especially those dealing with the topic of women

    oai_token-act-pair · gemini-2.0-flash

    bullet points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     المعيارى
    -0.79
     estekak
    -0.69
    routeProvider
    -0.59
     ISTAT
    -0.55
     calendriers
    -0.51
    shadowOpacity
    -0.50
    يكب
    -0.49
    WebElementEntity
    -0.49
    timewa
    -0.48
    enumi
    -0.48
    POSITIVE LOGITS
    intios
    0.58
    ierzch
    0.48
    pyplot
    0.47
     '?'
    0.46
    存于互联网档案馆
    0.46
     avar
    0.46
     Ith
    0.45
    productId
    0.45
     *)__
    0.43
    Chú
    0.43
    Activations Density 1.135%

    No Known Activations