Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 10279
    Prev
    Next
    INDEX
    Explanations

    the word "theatrical" as well as the word "actual"

    oai_token-act-pair · gemini-2.0-flash

    at actual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     actual
    -1.07
    Actual
    -0.98
    actual
    -0.97
     Actual
    -0.90
     själva
    -0.77
     ACTUAL
    -0.75
    ACTUAL
    -0.73
    themselves
    -0.71
    Сам
    -0.71
     selve
    -0.69
    POSITIVE LOGITS
     theater
    0.68
     theaters
    0.66
    icoot
    0.65
     Theaters
    0.57
     Theater
    0.57
    Theater
    0.56
     theatre
    0.55
     дописавши
    0.54
    ControllerAdvice
    0.54
    lüğ
    0.52
    Activations Density 0.455%

    No Known Activations