© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2427
    Prev
    Next
    INDEX
    Explanations

    the words "if" and "when" in the document

    oai_token-act-pair · gemini-2.0-flash

    if

    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
    setVerticalGroup
    -0.81
    ContentAsync
    -0.64
    audiovisuel
    -0.60
    ophor
    -0.58
    formKey
    -0.56
    avits
    -0.55
    CONSIN
    -0.55
     "..\..\
    -0.54
    émon
    -0.54
    EndContext
    -0.54
    POSITIVE LOGITS
     nonatomic
    0.56
    MemoryWarning
    0.55
    DockStyle
    0.54
    nonatomic
    0.51
    <bos>
    0.50
     kaynağından
    0.50
    Portail
    0.49
     uParam
    0.46
     ujednoznacz
    0.44
    WillAppear
    0.44
    Activations Density 2.084%

    No Known Activations